Power tool including a machine learning block
A power tool includes a housing and a sensor, a machine learning controller, a motor, and an electronic controller supported by the housing. The sensor is configured to generate sensor data indicative of an operational parameter of the power tool. The machine learning controller includes a first processor and a first memory and is coupled to the sensor. The machine learning controller further includes a machine learning control program configured to receive the sensor data, process the sensor data using the machine learning control program, and generate an output based on the sensor data using the machine learning control program. The electronic controller includes a second processor and a second memory and is coupled to the motor and to the machine learning controller. The electronic controller is configured to receive the output from the machine learning controller and control the motor based on the output.
1. A power tool comprising:
a housing;
a sensor supported by the housing and configured to generate sensor data associated with the power tool, wherein the sensor data includes one or more of motor speed data, motor current data, battery voltage data, and motion data of the power tool;
a machine learning controller including a first processor and a first memory, the machine learning controller supported by the housing, coupled to the sensor, and including a machine learning control program, the machine learning controller configured to:
receive the sensor data,
process the sensor data, using the machine learning control program, wherein the machine learning control program is a trained machine learning control program, and
generate, using the machine learning control program, an output based on the sensor data, wherein the output includes an indication of a detected application of the power tool, the application corresponding to at least one selected from the group of a type of fastener, a type of implement driven by the power tool, and a type of material on which the power tool is working;
a motor supported by the housing; and
an electronic controller including a second processor and a second memory, the electronic controller supported by the housing, coupled to the motor and to the machine learning controller, the electronic controller configured to:
receive the output from the machine learning controller, and
control the motor based on the output.
2. The power tool of claim 1 , wherein the machine learning control program is generated on an external system device through training based on example sensor data and associated outputs and is received by the power tool from the external system device.
3. The power tool of claim 2 , wherein the machine learning control program is a static machine learning control program.
4. The power tool of claim 1 , further comprising a wireless communication device configured to receive a machine learning control program update wirelessly from an external system device,
wherein the machine learning control program is an adjustable machine learning control program and the machine learning controller is configured to update the machine learning program based on the machine learning control program update.
5. The power tool of claim 4 ,
wherein the power tool is configured to receive feedback regarding the control of the motor based on the output and to provide the feedback and the sensor data to the external system device via the wireless communication device, and
wherein the machine learning control program update is generated by the external system device through further training based on the feedback and the sensor data.
6. The power tool of claim 1 , wherein the machine learning controller is further configured to:
receive feedback regarding the control of the motor based on the output,
provide the feedback to the machine learning control program to train the machine learning control program,
receive further sensor data from the sensor,
process the further sensor data, using the machine learning control program trained with the feedback, and
generate, using the machine learning control program trained with the feedback, a further output based on the further sensor data.
7. The power tool of claim 1 , wherein the machine learning controller is further configured to:
receive feedback from another power tool,
provide the feedback to the machine learning control program to train the machine learning control program,
receive further sensor data from the sensor,
process the further sensor data, using the machine learning control program trained with the feedback, and
generate, using the machine learning control program trained with the feedback, a further output based on the further sensor data.
8. The power tool of claim 1 , wherein the machine learning controller is further configured to receive a request to adjust, from user input, at least one selected from the group of a learning rate and a switching rate, and to adjust the at least one selected from the group of the learning rate and the switching rate of the machine learning control program based on the request.
9. The power tool of claim 1 , wherein the output indicates to the electronic controller at least one selected from the group of:
to change an operational threshold of the power tool,
to change to a stored operating mode profile,
a condition of at least one selected from the group of the power tool, a fastener being drive by the power tool, an accessory of the power tool, a workpiece on which the power tool is working,
a power tool event,
a power tool context,
an identity of a user of the power tool,
a rating of power tool performance,
a safety risk level, and
a condition of a user of the power tool.
10. A method of operating a power tool comprising:
generating, by a sensor of the power tool, sensor data associated with the power tool, wherein the sensor data includes one or more of motor speed data, motor current data, battery voltage data, and motion data of the power tool;
receiving, by a machine learning controller of the power tool, the sensor data, the machine learning controller including a first memory and a first processor configured to execute instructions stored on the first memory;
processing the sensor data, using a machine learning control program of the machine learning controller;
generating, using the machine learning control program, an output based on the sensor data, wherein the output data includes a condition of at least one selected from the group of a fastener being driven by the power tool, an accessory of the power tool, and a workpiece on which the power tool is working;
receiving, by an electronic controller of the power tool, the output from the machine learning controller, the electronic controller including a second memory and a second processor configured to execute instructions stored on the second memory; and
controlling, by the electronic controller, a motor of the power tool based on the output.
11. The method of claim 10 , further comprising:
receiving, by the machine learning controller, the machine learning control program from an external system device, wherein the machine learning control program is generated on the external system device through training based on example sensor data and associated outputs.
12. The method of claim 10 , further comprising:
receiving, by a wireless communication device of the power tool, a machine learning control program update wirelessly from an external system device; and
updating, by the machine learning controller, the machine learning program based on the machine learning control program update.
13. The method of claim 12 , further comprising:
receiving, by the power tool, feedback regarding the control of the motor based on the output; and
providing the sensor data and the feedback to the external system device via the wireless communication device, wherein the machine learning control program update is generated by the external system device through further training based on the sensor data and the feedback.
14. The method of claim 10 , further comprising:
receiving, by the machine learning controller, feedback regarding the control of the motor based on the output;
providing, by the machine learning controller, the feedback to the machine learning control program to train the machine learning control program;
receiving, by the machine learning controller, further sensor data from the sensor;
processing the further sensor data, using the machine learning control program trained with the feedback; and
generating, using the machine learning control trained with the feedback, a further output based on the further sensor data; and
controlling, by the electronic controller, the motor based on the output.
15. The method of claim 14 , further comprising:
receiving, by the machine learning controller, a request to adjust at least one selected from the group of a learning rate and a switching rate; and
adjusting the at least one selected from the group of the learning rate and the switching rate of the machine learning control program based on the request.
16. The method of claim 10 , wherein the output indicates to the electronic controller at least one selected from the group of:
to change an operational threshold of the power tool,
to change to a stored operating mode profile,
a condition of at least one selected from the group of the power tool, a fastener being drive by the power tool, an accessory of the power tool, a workpiece on which the power tool is working, and
a power tool event,
a power tool context,
an identity of a user of the power tool,
a rating of power tool performance,
a safety risk level, and
a condition of a user of the power tool.
17. The method of claim 10 , further comprising:
receiving an input, via an activation switch, disabling the machine learning program.
18. An external system device in communication with a power tool, the external system device comprising:
a first transceiver for wirelessly communicating with a second transceiver positioned within a housing of the power tool; and
a first machine learning controller in communication with the first transceiver, the machine learning controller including an electronic processor and a memory, the first machine learning controller configured to:
receive, via the first transceiver, tool usage data from the power tool from the second transceiver including feedback collected by the power tool,
train a machine learning control program using the tool usage data to generate an updated machine learning control program, the updated machine learning control program configured to be executed by a second machine learning controller of the power tool to cause the second machine learning controller of the power tool to:
receive power tool sensor data as input, wherein the sensor data includes one or more of motor speed data, motor current data, battery voltage data, and motion data of the power tool,
process the power tool sensor data, using the machine learning control program, and
provide an output, on which motor control is to be based, to a power tool electronic controller that controls a motor of the power tool based on the processed sensor data, wherein the output includes a detected application of the power tool; and
transmit, via the transceiver, the updated machine learning control program to the power tool.
19. The external system device of claim 18 , wherein the external system device is at least one selected from the group of a server, a smart telephone, a tablet computer, a laptop computer, and a wireless hub.
20. The external system device of claim 18 , wherein the feedback is at least one selected from the group of positive feedback indicating a correct classification by the machine learning program and negative feedback indicating an incorrect classification by the machine learning program.
21. The external system device of claim 18 , wherein the output indicates to the electronic controller at least one selected from the group of:
to change an operational threshold of the power tool,
to change to a stored operating mode profile,
a condition of at least one selected from the group of the power tool, a fastener being drive by the power tool, an accessory of the power tool, a workpiece on which the power tool is working, and
the detected application of the power tool, wherein the application corresponds to at least one selected from the group of a type of fastener, a type of implement driven by the power tool, and a type of material on which the power tool is working,
a power tool event,
a power tool context,
an identity of a user of the power tool,
a rating of power tool performance,
a safety risk level, and
a condition of a user of the power tool.
22. The external system device of claim 18 , wherein the first machine learning controller is further configured to:
receive, via the first transceiver, further tool usage data from another power tool including further feedback collected by the power tool, and
train the machine learning control program using the further tool usage data to generate the updated machine learning control program that is transmitted to the power tool.