Method for controlling a hand-held power tool and hand-held power tool

Abstract

The invention relates to a method (200) for controlling a hand-held power tool (100), comprising: receiving (201) sensor data of at least one operating variable (119) of the hand-held power tool (100); receiving (203) an input value, based on a user input from a user of the hand-held power tool (100), for a control parameter of the hand-held power tool (100); determining (205) a first target value of the control parameter based on the sensor data and the input value; executing (207) a state determination module (107) on the sensor data and determining an operating state (A, B, C) of the hand-held power tool (100); and controlling (209) the hand-held power tool (100) based on the first target value of the control parameter and on the determined operating state (A, B, C).

Description

[0001] Description

[0002] title

[0003] Method for controlling a hand-held power tool and hand-held power tool

[0004] The invention relates to a method for controlling a handheld power tool. The invention further relates to a corresponding handheld power tool configured to carry out the method.

[0005] State of the art

[0006] Methods for controlling hand-held power tools are known from the state of the art.

[0007] It is an object of the invention to provide an improved method for controlling a hand-held power tool and a hand-held power tool.

[0008] This object is achieved by the method for controlling a handheld power tool and the handheld power tool of the independent claims. Advantageous embodiments are the subject of the subordinate claims.

[0009] According to one aspect of the invention, a method for controlling a hand-held power tool is provided, comprising:

[0010] Receiving sensor data of at least one operating variable of the handheld power tool; Receiving an input value for a control parameter of the handheld power tool based on a user input from a user of the handheld power tool;

[0011] Determining a first target value of the control parameter based on the sensor data and the input value;

[0012] Executing a state determination module and applying the state determination module to the sensor data and determining an operating state of the handheld power tool; and

[0013] Controlling the handheld power tool based on the first target value of the control parameter and the determined operating state.

[0014] This makes it possible to achieve the technical advantage of providing an improved method for controlling a handheld power tool, in which method, in addition to a user input from a user of the handheld power tool, an operating state determined during operation of the handheld power tool is also taken into account when controlling the handheld power tool. For this purpose, an operating state of the handheld power tool is determined based on sensor data of at least one operating variable of the handheld power tool by executing a state determination module on the sensor data. The control of the handheld power tool is then effected taking the determined operating state into account. According to various embodiments, the control of the handheld power tool can be adapted precisely to the existing operating state. In this case, the control can also take place independently of the user input from the user.For example, the user input can be adapted to the current operating state so that control of the hand-held power tool is possible that is appropriate to the operating state, even if the user input would result in a different control that is not appropriate to the operating state.

[0015] According to one embodiment, controlling the hand-held power tool comprises:

[0016] Determining a second target value of the control parameter based on the determined operating state of the handheld power tool; determining an output target value of the control parameter based on the first target value and the second target value; and outputting the output target value to an actuator of the handheld power tool for controlling the handheld power tool.

[0017] This can achieve the technical advantage of precisely adapting the control of the handheld power tool to the current operating state. For this purpose, the control of the handheld power tool is based on first and second target values ​​of a control parameter. The first target value is based on a user input from the user of the handheld power tool. The second target value, however, is determined taking into account the determined operating state of the handheld power tool. Taking into account the first and second target values ​​of the control parameter, an output target value of the control parameter is then determined, which is then output to the actuators of the handheld power tool to control the handheld power tool.

[0018] By taking the first and second target values ​​into account, both the user input and the current operating state of the handheld power tool can be considered for determining the output target value for the control of the handheld power tool. This has the advantage that, particularly in cases where the user input, for example, by actuating a trigger switch, does not allow for optimal control of the handheld power tool for the current operating state of the handheld power tool, by taking into account the second target value adapted to the current operating state, the control can still be adapted to the current operating state despite the inappropriate user input.

[0019] By taking into account the first target value based on the user input, control of the handheld power tool nevertheless remains primarily in the hands of the user. Only for certain operating states can the user input be overwritten or better adapted to the current operating state in the form of the output target value, which takes into account the second target value. The method thus enables control of the handheld power tool that is adapted to the respective operating state of the handheld power tool. In addition to the user input, this method also takes into account target values ​​of a control parameter that are adapted to the respective operating states of the handheld power tool.

[0020] In the sense of the application, a target value is a desired value of the control parameter.

[0021] According to one embodiment, determining the output target value comprises: defining the output target value as a minimum value or a maximum value of the first and second target values ​​and / or

[0022] Define the output target value as a product of the first and second target values.

[0023] This can achieve the technical advantage of determining the most precise output target value of the control parameter. By defining the output target value as a minimum or maximum value between the first and second target values, the simplest possible determination of the output target value is achieved. Depending on the determined operating state of the handheld power tool and the type of control parameter, the selected minimum or maximum value between the first and second target values ​​of the control parameter can be used to determine an output target value of the control parameter that is optimally adapted to the respectively determined operating state. This enables the handheld power tool to be controlled in a way that is as precise as possible to the respective operating state.

[0024] The control parameter can, for example, be a speed or torque of a motor of the handheld power tool. The operating state of the handheld power tool can, for example, describe the work progress of the handheld power tool. If the handheld power tool is designed as an electric screwdriver, for example, an operating state of the handheld power tool can describe that the screw to be tightened is already screwed into the respective workpiece with a positive fit.

[0025] The target speed or torque of the motor entered by the user by pressing the trigger switch of the handheld power tool may be too high for such a positive locking of the screw to be screwed in. Therefore, taking into account the respective operating state determined, the second output target value calculated in the form of a correspondingly lower motor speed or a correspondingly lower motor torque, the output target value of the control parameter describes a reduced speed or a reduced torque of the handheld power tool motor compared to the user input. The output target value can thus be used to achieve control of the handheld power tool that is optimally adapted to the respective operating state.

[0026] By defining the output target value as the maximum or minimum value of the first and second target values, the target value that best fits the current operating state can be selected as the output target value. In particular, the target value can be limited to a value range appropriate for the current operating state compared to the input parameter.

[0027] By multiplying the first and second target values, the second target value can act as a sensitivity factor with respect to the first target value. The second target value can thus increase or decrease the first target value, which is based on the user input, with respect to the current operating state by a factor in the form of the second target value. The user input and the resulting control of the handheld power tool by the user can thus be efficiently adapted to the current operating state.

[0028] According to one embodiment, determining the output target value comprises: defining the output target value as the first target value if the second target value is less than a predefined threshold, and defining the output target value as a predefined target value if the second target value is greater than or equal to the predefined threshold.

[0029] This allows the technical advantage of providing a more precise output target value that is optimally adapted to the current operating state of the handheld power tool. For this purpose, either the first target value based on the user input or a predefined target value is used as the output target value, depending on the second target value in relation to a predefined threshold.

[0030] Taking the predefined threshold value into account enables simple and precise adjustment of the output target value to the respective operating state. Depending on the type of operating state, the predefined target value as well as the predefined threshold value of the control parameter can be adjusted such that the resulting output target value enables optimal control of the handheld power tool.

[0031] The second value of the control parameter, determined based on the respective operating state, can thus serve as the switching value for the first target value of the user input. Depending on the assessment of the second target value in relation to the predefined threshold, a switch is made between the first target value of the user input and the predefined target value as the output target value.

[0032] According to one embodiment, determining the output target value comprises: defining the output target value as a product of the first target value with a first predefined target value if the second target value is less than a predefined threshold, and defining the output target value as a product of the first target value with a second predefined target value if the second target value is greater than or equal to the predefined threshold. This makes it possible to achieve the technical advantage that a further more precise output target value can be provided. Depending on the second target value determined with respect to the determined operating state and a predefined threshold, the output target value is defined as a product of the first target value based on the user input with a first predefined target value or a second predefined target value.The first and second predefined target values ​​can be designed as constant target values.

[0033] As in the previous embodiment, the predefined target values ​​as well as the predefined threshold value can each be adapted to the current operating state. The first and second predefined target values ​​in turn serve as sensitivity values, which, when multiplied by the first target value, increase or decrease the first target value, thereby adapting it to the current operating state.

[0034] The second target value determined with respect to the operating state serves as a switching value, in that the second target value is connected between the product of the first target value with the first predefined target value and the product of the first target value with the second predefined target value, with respect to the respective predefined threshold value. This enables the output target value to be adjusted as precisely as possible to the respective determined operating state.

[0035] According to one embodiment, determining the operating state comprises: predicting an event time, wherein at the event time a transition of the hand-held power tool occurs from one operating state to another operating state.

[0036] This allows the technical advantage of being able to predict, in addition to actually determining an existing operating state, an event time that defines a transition between different operating states of the handheld power tool. By predicting the event time, the control system of the handheld power tool can be adapted to an impending transition to a further operating state. This enables the most precise control of the handheld power tool possible, as the control system can be adapted to events that have not yet occurred or operating states that the handheld power tool will only enter in the future.

[0037] According to one embodiment, the control parameter comprises one or more from the list: motor speed, motor current, motor power of a motor of the hand-held power tool.

[0038] This provides the technical advantage of enabling precise control of the handheld power tool, taking into account the output target values ​​of the control parameters. The motor speed, motor current, and motor power of the handheld power tool's motor represent reliable control parameters on which control of the handheld power tool is possible.

[0039] According to one embodiment, the operating variable comprises one or more from the list: motor current, motor position angle, motor rotational speed, voltage of a voltage source of the hand-held power tool, movements and / or vibrations of the hand-held power tool or in the hand-held power tool.

[0040] This can achieve the technical advantage that the operating variable provides a useful measurement for determining the operating state. By measuring the motor current, the motor position angle, the motor rotational speed, the operating voltage of a voltage source of the hand-held power tool, or movements and / or vibrations of or within the hand-held power tool, meaningful information can be obtained on the basis of which the operating state of the hand-held power tool can be determined. For example, in the above example, measuring the motor current can be used to determine whether a screw to be screwed in is already screwed into the workpiece to be machined with a positive fit. When the positive fit is achieved, changes in the motor current as well as the motor rotational speed or motor rpm can be detected, thus enabling a precise determination of the operating state.For example, the movement signals can also be used to detect whether the handheld power tool, such as a screwdriver, has been moved to the next work location, thus completing the previous work phase, i.e., the previous screwing process. This allows the operating state to be reset at the appropriate time, corresponding to the new work phase, i.e., the new screwing process.

[0041] According to one embodiment, the operating state comprises one or more from the list: a load range in which the hand-held power tool is operated, a strength of vibrations in the hand-held power tool and / or on a machined workpiece and / or in the user of the hand-held power tool, a temperature in the hand-held power tool and / or on the workpiece, operating mode in which the hand-held power tool is operated, a work progress of the hand-held power tool, material of the workpiece, existence of a positive connection between the hand-held power tool and the workpiece.

[0042] This makes it possible to achieve the technical advantage that various operating states in which the handheld power tool may be or enter can be taken into account when controlling the handheld power tool in the form of the second target value of the control parameter. The method according to the invention thus allows a wide variety of operating states to be taken into account, thereby providing a widely applicable control method.

[0043] According to one embodiment, the state determination module comprises a trained artificial intelligence that is trained to determine the operating state of the handheld power tool and / or to predict the time of the event based on the sensor data of the operating variable.

[0044] This can achieve the technical advantage of providing a condition determination module that is as reliable and powerful as possible and is designed to detect existing operating states or predict future event times.

[0045] A method is provided for generating a training data set for training an artificial intelligence for determining an operating state and / or for predicting an event time of a handheld power tool, the method comprising:

[0046] Providing a plurality of measured values ​​of an operating variable of a hand-held power tool, wherein the measured values ​​are each provided with time stamps;

[0047] Identifying an event time within the plurality of measured values, wherein the event time defines a time at which the handheld power tool transitions from a first operating state to a second operating state;

[0048] Providing the measured values ​​with label values ​​that are suitable for indicating whether a respective measured value is assigned to the event time and / or the event time range;

[0049] Arranging the plurality of labeled measured values ​​in a time series based on the timestamps of the measured values; and

[0050] Providing a training data set comprising the time series of labeled measured values ​​of the farm size.

[0051] This makes it possible to achieve the technical advantage of providing an improved method for generating a training data set for training an artificial intelligence system for determining an operating state and / or predicting an event time of a handheld power tool. Accordingly, an improved training data set can be provided that is optimally adapted to training an artificial intelligence system for determining an operating state or predicting event times in the sense of the method for controlling a handheld power tool according to the above embodiments.

[0052] For this purpose, measured values ​​of an operating variable of the hand-held power tool are first provided, wherein the measured values ​​are each provided with a time stamp. The measured values ​​can be based on a plurality of measurements of the operating variable of the hand-held power tool or a plurality of comparable hand-held power tools. The corresponding measured values ​​can, for example, be recorded during operation of the hand-held power tool or during operation of the plurality of hand-held power tools and provided as a corresponding measurement of measured values ​​for the method for generating the training data set. The measured values ​​of the operating variable recorded during operation of the hand-held power tools can, for example, be transferred to a dedicated server architecture that is configured to provide the corresponding measurement sets for the method for generating the training data set.

[0053] Furthermore, based on the timestamps that define a point in time at which the respective measured values ​​were recorded, an event time is identified within the plurality of measured values ​​as the point in time at which the handheld power tool transitions from a first to a second operating state. Furthermore, the measured values ​​are provided with label values ​​that identify the respective event time. Furthermore, the plurality of labeled measured values ​​are arranged in a time series, and the time series of the labeled measured values ​​is provided as the corresponding training data set.

[0054] Based on a training data set generated in this way, in which the labeled measured values ​​of the operating variable are arranged in a corresponding time series with respect to their timestamps, an optimized training of an artificial intelligence can be carried out to determine an operating state or to predict an event time. The respective labels of the measured values ​​of the operating variable allow an assessment of whether the handheld power tool was in a first or a second operating state at the time of the respective measured value.

[0055] Furthermore, at least one label of the measured value allows the precise determination of the event time at which the transition between the two operating states occurs. Assigning label values ​​to the measured values ​​corresponds to the labeling of measured values ​​known from the prior art, in which each measured value of the operating variable is assigned the corresponding label as an identification.

[0056] According to one embodiment, the method further comprises:

[0057] Determining a rotation angle of a motor of the hand-held power tool for each measured value of the operating variable; and

[0058] Calculating a rotation time for each measured value of the operating variable, taking into account a time period required to execute a complete revolution of the motor and the time stamp, wherein the rotation time defines a time at which a complete revolution of the motor is completed for a measured value based on the respective time stamp.

[0059] This can achieve the technical advantage of further improving the training data set. For each measured value of the operating variable, a rotation angle of the hand-held power tool motor that existed at the time the measured value of the operating variable was recorded is determined. Furthermore, a rotation time is calculated for each measured value of the operating variable, whereby the rotation time describes a point in time at which, based on the respective rotation angle of the respective measured value of the operating variable, a complete rotation has been completed. By having both time stamps and rotation angles, all other sensor signals can be related to either time or rotation angle. This improves the data set, as states and events are available and can be evaluated both over time and over the course of the rotation angle progression. Based on the rotation angle or the rotation angle assigned to each measured value.A precise prediction of the event time can be made based on the rotation time. By knowing the rotation time at which the handheld power tool motor has completed another complete rotation for each measured value of the operating variable with the corresponding timestamp, the event time can be precisely predicted for each measured value of the operating variable and the corresponding timestamp, taking into account the number of motor rotations required to achieve the transition to the second operating state. This enables optimal training of the artificial intelligence.

[0060] According to one embodiment, identifying the event time comprises: receiving sensor data that represents the operating state of the handheld power tool;

[0061] Determining the event time within a time series of sensor data; synchronizing the time series of the operating variable with the time series of the sensor data; and

[0062] Identify the event time in the operating variable time series based on the event time of the sensor data time series.

[0063] This can achieve the technical advantage of further improving the method for generating a training data set and further improving the correspondingly generated training data set. For this purpose, sensor data from another sensor is taken into account to identify the operating states or to determine the time of the event. The sensor data depicts the hand tool in its respective operating state and is suitable for identifying the time of the event. For this purpose, the sensor data also includes timestamps that define the times at which the sensor data was recorded.

[0064] The sensor data are arranged in a corresponding time series according to their timestamps, and the event time within the time series is determined based on the respective timestamps. Subsequently, the time series of the measured values ​​of the operating variable and the time series of the sensor data are synchronized according to the respective timestamps. Based on the event time within the time series of the sensor data, the event time within the time series of the operating variable is subsequently identified. The additional information from the sensor data allows for a more precise determination of the event time within the time series of the measured values ​​of the operating variable. This allows for a more precise training dataset.

[0065] According to one embodiment, the sensor data are data from an external sensor, in particular a camera sensor.

[0066] This offers the technical advantage of further improving the method for generating a training data set. The sensor data is based on data from an external sensor. This can be implemented, for example, as a camera sensor. The camera data from the camera sensor can be used to map the operation of the handheld power tool during which the measured values ​​of the operating variable were recorded. By mapping the operation of the handheld power tool, the various operating states can be clearly represented in the sensor data.

[0067] This allows the event time at which the handheld power tool transitions from the first operating state to the second operating state to be clearly identified. The event time can, for example, describe the point in time at which, in the example described above, the positive connection between the screw and the workpiece is achieved when screwing the screw into the workpiece. This point in time can be clearly identified using the camera data from the camera sensor that maps the screwing process of the handheld power tool. This allows the event time to be clearly identified by taking into account the time stamps of the camera data, which identify the time at which the camera data was recorded.

[0068] By synchronizing the two time series, the measurement data of the

[0069] By combining the operating variable and the camera data, the time at which the positive connection between the screw and the workpiece is achieved can be precisely identified in the time series of the measured data of the operating variable. By appropriately labeling the measured values ​​of the operating variable, in which the identified event time is marked, the artificial intelligence can be trained based on the measured data of the operating variable to determine the various operating states of the handheld power tool or to predict the event time. This enables a precise training data set on which optimized training of an artificial intelligence for determining operating states or predicting event times is possible.

[0070] A method for training an artificial intelligence to determine an operating state of a handheld power tool is provided, the method comprising:

[0071] Providing a training data set generated according to the inventive method for generating a training data set according to one of the preceding embodiments; and

[0072] Executing a training of the artificial intelligence to determine an operating state and / or to predict an event time of a handheld power tool based on the training data set.

[0073] This makes it possible to achieve the technical advantage of providing an improved method for training artificial intelligence, which is suitable for training the artificial intelligence to recognize operating states of a handheld power tool and to predict event times at which a transition between operating states of the handheld power tool occurs, according to the method according to the invention for controlling a handheld power tool. By using the training data set according to the invention, the training of the artificial intelligence is adapted to the application of the artificial intelligence in controlling the handheld power tool according to the method for controlling a handheld power tool, so that optimal training results and optimally trained artificial intelligences can be achieved.An artificial intelligence is provided for determining an operating state of a hand-held power tool and / or for predicting an event time according to the method according to one of the preceding embodiments, wherein the artificial intelligence is trained according to the inventive method for training an artificial intelligence.

[0074] This makes it possible to achieve the technical advantage of providing a state determination module for a control system of the handheld power tool according to the inventive method for controlling a handheld power tool that is as reliable and powerful as possible, which is configured to recognize the respective operating states of the handheld power tool or to predict event times at which a transition between operating states occurs. By training the artificial intelligence according to the inventive method for training artificial intelligence, the artificial intelligence is optimally configured for use in a control system of a handheld power tool according to the method for controlling a handheld power tool.

[0075] According to one embodiment, the artificial intelligence is designed as an artificial neural network, in particular as a network with at least one recurrent layer with an internal state memory.

[0076] This can achieve the technical advantage of providing particularly reliable and powerful artificial intelligence. The artificial neural network can be designed, in particular, as a long-short-term memory (LSTM) network. The LSTM network is particularly suitable for detecting and determining operating states of the handheld power tool and predicting event times at which a transition between different operating states occurs. LSTM networks are known from the state of the art for pattern recognition and predicting behavior or events based on historical data. Implementing the neural network as an LSTM network (long-short-term memory) is suitable as a network layer and can be combined with other network layers in a network.

[0077] According to a further aspect, a computing unit is provided which is configured to execute the method for controlling a hand-held power tool according to one of the preceding embodiments and / or the method for generating a training data set according to one of the preceding embodiments and / or the method according to the invention for training an artificial intelligence and / or the artificial intelligence according to the invention.

[0078] According to a further aspect, a computer program product comprising instructions is provided which, when the program is executed by a data processing unit, cause the data processing unit to execute the method for controlling a hand-held power tool according to one of the preceding embodiments and / or the method for generating a training data set according to one of the preceding embodiments and / or the method according to the invention for training an artificial intelligence and / or the artificial intelligence according to the invention.

[0079] According to a further aspect, a hand-held power tool is provided with a computing unit and at least one sensor for determining sensor data of at least one operating variable of the hand-held power tool, wherein the computing unit is designed to carry out a method for controlling the hand-held power tool, wherein the method comprises: receiving sensor data of at least one operating variable of the hand-held power tool;

[0080] Receiving an input value for a control parameter of the handheld power tool based on a user input from a user of the handheld power tool;

[0081] Determining a first target value of the control parameter based on the sensor data and the input value; executing a state determination module on the sensor data and determining an operating state of the handheld power tool;

[0082] Determining a second target value of the control parameter based on the determined operating state of the handheld power tool;

[0083] Determining an output target value of the control parameter based on the first target value and the second target value; and

[0084] Outputting the output target value to an actuator of the handheld power tool to control the handheld power tool.

[0085] This makes it possible to achieve the technical advantage that an improved hand-held power tool can be provided which is configured to carry out the method for controlling a hand-held power tool with the above-mentioned technical advantages.

[0086] Embodiments of the invention are explained with reference to the following drawings. The drawings show:

[0087] Fig. 1 is a schematic representation of a hand-held power tool according to an embodiment;

[0088] Fig. 2 shows a further schematic representation of a hand-held power tool, in which individual functional sequences of the hand-held power tool are illustrated;

[0089] Fig. 3 shows time courses of an operating variable of a hand-held power tool and a rotation angle of a motor of the hand-held power tool;

[0090] Fig. 4 is a schematic representation of a hand-held power tool according to an embodiment, wherein the hand-held power tool is shown in different operating states;

[0091] Fig. 5 shows a schematic representation of a drive control of the handheld power tool according to one embodiment; Fig. 6 shows a flowchart of a method for controlling a handheld power tool according to one embodiment;

[0092] Fig. 7 shows a further flowchart of the method for controlling a hand-held power tool according to a further embodiment;

[0093] Fig. 8 shows a further flowchart of the method for controlling a hand-held power tool according to a further embodiment;

[0094] Fig. 9 is a schematic representation of an artificial intelligence configured to be used in a control system of the hand-held power tool;

[0095] Fig. 10 is a flowchart of a method for generating a training data set for training an artificial intelligence according to an embodiment;

[0096] Fig. 11 shows a further flowchart of a method for generating a training data set for training an artificial intelligence according to a further embodiment;

[0097] Fig. 12 is a flowchart of a method for training an artificial intelligence; and

[0098] Fig. 13 is a schematic representation of a computer program product.

[0099] Fig. 1 shows a schematic representation of a hand-held power tool 100 according to an embodiment.

[0100] The exemplary handheld power tool 100 comprises a motor 101 with a motor controller 103. The handheld power tool 100 further comprises a computing unit 105 on which a state determination module 107 is installed and executable. The computing unit 105 with the state determination module 107 is configured to execute the inventive method for controlling a handheld power tool 100. The handheld power tool 100 further comprises a voltage source 111 and a current measuring device 113. The handheld power tool 100 further comprises a trigger switch 109, by means of which the handheld power tool 100 can be controlled by a user. In addition, the handheld power tool 100 comprises an adjustment device 115 with which various operating modes of the handheld power tool 100 can be set. Finally, the handheld power tool 100 comprises a tool 117, by means of which corresponding work processes can be carried out by executing the handheld power tool 100.

[0101] The handheld power tool 100 can be designed, for example, as a screwdriver or a battery-operated screwdriver. For this purpose, the tool 117 can be designed, in particular, as a holder for replaceable screwdriver blades.

[0102] The illustrated engine control unit 103 may, in particular, include an associated power unit of the engine control unit. The engine 101 may further include a corresponding transmission, which is not explicitly shown in Fig. 1.

[0103] The motor 101 can be designed, for example, as a mechanically or electrically commutated DC motor. The corresponding gearing can be designed as a planetary gear.

[0104] According to the invention, the power section of the motor controller 103 can convert a control signal, for example via PWM pulse width modulation, into the voltage or current waveforms required for the motor 101. For this purpose, the control signals can first be converted into corresponding digital signals, after which the correspondingly converted signal can be transmitted via a suitable data bus, for example I2C or SPI. In the case of an electrically commutated DC motor, a corresponding rotating field can be generated, which can be tracked synchronously with the rotation of the rotor. The motor controller can implement voltage-controlled or speed-controlled control. With voltage-controlled control, the motor speed is reduced as the load (torque) increases and the operating current increases. Information on the motor speed or the angle of rotation can be derived system-inherently from the phase changes.Additionally or alternatively, a continuous rotation angle sensor (not shown in Fig. 1) can be used to detect the rotor position. Such a rotor position signal can be transmitted to the computing unit 105 for controlling the handheld power tool 100. This signal transmission can, in turn, be carried out via PWM, I2C, SPI, or analog.

[0105] According to one embodiment, instead of the angle sensor, an algorithm is implemented in a control unit that infers the angle of rotation based on the measured motor currents and voltages, which include signal components resulting from voltages induced back into the rotor. In this embodiment, the angle sensor can be functionally replaced by the algorithm.

[0106] The power supply via voltage source 111 can be provided by a plurality of battery elements, for example, lithium-ion cells. Overcharging, overcurrents, and deep discharges can be prevented by an appropriate battery management system.

[0107] According to one embodiment, the trigger switch 109 can be embodied as a potentiometer that provides the computing unit 103 for controlling the handheld power tool 100 with analog control signals that correspond to the linear actuation of the trigger switch 109. Actuation of the trigger switch 109 can provide corresponding user inputs for controlling the handheld power tool 100.

[0108] The current measuring device 113 can determine the battery current of the voltage source 111, which is dominated by the motor current of the motor 101. The controller typically has a current consumption of less than 200 milliamperes. A low-ohm resistor or a Hall sensor can be used as the measuring element. Using an amplifier circuit and level adjustment, a current-proportional analog signal can be provided to the computing unit 103, which controls the handheld power tool 100.

[0109] The adjustment device 115 can be designed as a rotary potentiometer, a rocker switch, or a double switching element. The threshold value required for the automatic function must be user-influential.

[0110] The computing unit 101 can comprise a microcontroller with conventional circuitry (voltage regulator, clock source, EMC measures) and a communication device (Bluetooth, 4G, WLAN). The microcontroller can comprise an analog-to-digital converter and digital interfaces to generate and detect the signals of the trigger switch 109, the setting device 115, the current measuring device 113, the supply voltage, the motor speed, and the control signals of the motor 101. The microcontroller (not explicitly shown in Fig. 1) can implement the state determination module 107 for executing the inventive method for controlling the handheld power tool 100.

[0111] The handheld power tool 100 can be configured as a screwdriver, an impact wrench, or a simple cordless screwdriver. Alternatively, the handheld power tool 100 can be configured as an electric drill, a percussion drill, a hammer drill, or a drill bit.

[0112] Fig. 2 shows a further schematic representation of a hand-held power tool 100, in which individual functional sequences of the hand-held power tool 100 are illustrated.

[0113] Fig. 2 shows a further schematic representation of an embodiment of the handheld power tool 100 according to the invention. The handheld power tool 100 comprises the motor 101, the computing unit 105, which is arranged on a circuit board 127, the energy source 109, and the tool 117. The graphic representation shown illustrates some of the functionalities of the handheld power tool 100. Some of the components of the handheld power tool 100 from Fig. 1 are shown, while other components are not shown in order to keep the representation as simple as possible. However, the handheld power tool 100 shown can include all of the components shown in Fig. 1.

[0114] In addition to the computing unit 105, which, as already described above, can be designed as a microcontroller or can comprise such a microcontroller, and on which the state determination module 107 shown in Fig. 1 is installed according to the invention, a speed sensor 129, by means of which a motor speed of the motor 101 can be measured, and a vibration sensor 131, by means of which vibrations of the hand-held power tool 100 can be measured, and an inverter 133 are also installed on the circuit board 127.

[0115] Via the trigger switch 109, a user of the handheld power tool 100 can transmit user inputs 139 to the computing unit 105 by means of an electrical signal transmission 147. The power of the handheld power tool 100 can be controlled via the user inputs 139, which include, for example, a trigger level of the trigger switch 109. Furthermore, the user inputs 139 can specify directions of rotation of the motor 101, which define, for example, a screwing or drilling direction, or operating modes of the handheld power tool 100, which describe, for example, a screwing process with or without an impact function.

[0116] Based on the user inputs 139, the computing unit 105 controls the control of the handheld power tool 100 and outputs corresponding control signals to the inverter 133 via an electrical signal transmission 147. The inverter 133 outputs a corresponding electrical energy transmission 141 to the motor 101. The motor 101 effects a power transmission 135 to the tool 117 via a corresponding force-torque transmission 143, by means of which the workpiece 137 can be machined. According to the invention, the method for controlling a handheld power tool 100, which is carried out by the computing unit 105, uses measured values ​​of an operating variable on the basis of which operating states of the handheld power tool 100 are determined. The operating variable can be, for example, the motor current, a motor power, as well as a speed or torque of the motor 101.In the embodiment shown, the motor speed of motor 101 is taken into account as the operating variable on which operating states of handheld power tool 100 are determined based on the method according to the invention. This is measured by the illustrated speed sensor 129, which detects the movement 145 of motor 101. Furthermore, in the embodiment shown, vibrations / movements 145 of handheld power tool 100, or of tool 117, or of workpiece 137, are taken into account as an operating variable. The vibrations / movements are measured by vibration sensor 131. Corresponding measurement signals are forwarded from speed sensor 129 and vibration sensor 131 to computing unit 105 for further processing.

[0117] The vibration sensor 131 can be designed, for example, as an acceleration sensor.

[0118] According to the invention, to control the handheld power tool 100, the measured rotational speed or the detected vibrations are analyzed by executing a state determination module 107, and a current operating state of the handheld power tool 100 is determined. Based on the determined operating state, the control of the handheld power tool 100 is adjusted accordingly.

[0119] For a more detailed description of the method according to the invention for controlling the hand-held power tool 100, reference is made to the description of the following figures.

[0120] The power transmission 135 of the handheld power tool 100 can be implemented as a direct drive or via a gear. Furthermore, the drive of the handheld power tool 100, which is only schematically indicated in Figures 1 and 2, can include various drive options, such as a percussion mechanism, a hammer mechanism, or a chisel mechanism.

[0121] As already mentioned, the power of motor 101 can be transmitted to the drive of handheld power tool 100 via a transmission. This transmission can be configured, for example, as a manual transmission with two, three, or more gears. The transmission can be connected to a slip clutch, which in turn has a direct connection to the drive. An alternative solution without a slip clutch, in which the transmission is directly connected to the drive, is also conceivable.

[0122] The vibrations or movements measured by the vibration sensor 131 can, for example, include movements of the handheld power tool 100 triggered by the user of the handheld power tool 100. Furthermore, the movements or vibrations can be caused by the motor, the transmission, or the drive. Alternatively, the movements or vibrations measured by the vibration sensor 131 can be caused by the movement of a bit on a screw head or result from the force exerted by the screw on the workpiece 137 to be machined.

[0123] Fig. 3 shows temporal courses of an operating variable 119 of a hand-held power tool 100 and a rotation angle a ro t of a motor 101 of the hand tool 100.

[0124] Graph a) shows a temporal progression of an operating variable 119 of a handheld power tool 100. In the embodiment shown, the operating variable 119 describes a motor current of a motor 101 of a handheld power tool 100. In the embodiment shown, the handheld power tool 100 is designed as a screwdriver, and the progression of the operating variable 119 shown shows the temporal progression of the motor current in a screwing operation in which a self-tapping screw is screwed into a workpiece 137 made of wood or a comparable material.

[0125] The temporal progression of the operating variable 119 describes a time series 123 consisting of a plurality of chronologically ordered measured values ​​121 of the motor current. The measured values ​​121 were recorded during operation of the handheld power tool 100, i.e., when screwing the screw into the workpiece, by a corresponding current sensor within the handheld power tool 100.

[0126] Graphic a) describes a typical curve of the motor current I when screwing a self-tapping screw into wood or similar materials. The motor current I represents the torque output by the motor 101 through the torque constant with the unit Newton meters per ampere. The torque resulting from the starting current is used to accelerate the rotor of the electric motor 101 at the beginning of the screwing operation. This results in the peak of the motor current I occurring at the beginning of time series 123. Following the start-up of the rotor, the speed is largely constant, which causes the almost horizontal curve of the motor current I.

[0127] This range, in which the starting peak and subsequently the almost horizontal course of the motor current I is detected, is characterized in graph a) by operating state A. In this operating state A, a large part of over 90% of the applied torque is converted into actual mechanical work on the screw or the workpiece, and the screw is screwed into the workpiece accordingly.

[0128] In graphic a), two event times 125, 126 are also marked, in which a transition between the operating state A, first into an operating state B and subsequently into a further operating state C takes place.

[0129] In the area of ​​event time 126, the motor current I in the operating state

[0130] A a uniform increase. This is due to the further screwing of the screw into the workpiece, which requires an ever greater torque with increasing screw-in depth, the generation of which requires an increasing motor current I.

[0131] Starting from event time 126, there is a steeper increase in motor current I compared to the relatively gentle increase in operating state A. This increasingly steep increase in motor current I is caused by the conical screw head of the self-tapping screw resting on the surface of the workpiece to be machined. At event time 126, the conical screw head of the self-tapping screw hits the surface of the workpiece. Operating state B is therefore characterized by the conical screw head being screwed into the workpiece. Due to the conical shape of the screw head, an increased torque is required to screw the screw head into the workpiece, which explains the steep increase in motor current I.

[0132] Event time 125, on the other hand, describes the transition from operating state B, in which the conical screw head is screwed into the workpiece, to operating state C, in which the screw head is fully screwed into the workpiece. Event time 125 describes the point at which the screw head is flush with the surface of the workpiece. This point in time is also referred to as the flush point. The point in time marked by event time 126, at which the conical screw head makes contact with the surface of the workpiece, is also referred to as the pre-flush point.

[0133] In the illustrated embodiment, a flattening curve of the motor current I is shown in operating state C. This can be caused by shearing off the head or by damage to the workpiece material when the screw is tightened further beyond the flush point. Graphic b) shows a temporal curve of a rotation angle a. rot. The time course shows an example of the signal from an angle sensor. In the example shown, the sensor has a uniqueness range of 360°. This is not required; smaller uniqueness ranges are equally sufficient. As a rule, the uniqueness range of the sensor can be coupled to the speed of the motor 101. Absolute angle information for the entire screwdriving process from the beginning (actuation of the trigger switch 109 by the user) to the desired shutdown can be obtained from the angle sensor signal using so-called phase unwrapping. For this purpose, knowledge of the continuous rotation of the motor 101 can be used to determine that the change from plus 180° to, for example, minus 179° actually corresponds to a rotation angle of plus 181°.

[0134] In graph b) rotation times t ro t. At the rotation times t rot a complete rotation of the motor 101 has occurred. The knowledge regarding the rotation times t ro t or the rotation angle a ro t of the motor 101 can subsequently be used to predict the event times 125, 126. Upon reaching the above-described event time 126, at which the conical screw head rests on the surface of the workpiece, the event time 125 at which the screw is flush with the surface of the workpiece can be predicted with knowledge of the rotation angle. Graphic b) also shows a rotation angle difference A ro t as a difference between the angles of rotation a ro t at event times 125, 126.

[0135] The situation shown in Fig. 3 is intended to illustrate only one possible application of the method according to the invention by way of example. Other applications in which the hand-held power tool 100 is not designed as a screwdriver but, for example, as a drill, chisel, or jigsaw, are also intended to be covered by the present invention. More or fewer and differently configured operating states (A, B, C) can also be taken into account than those described in this example. For example, the hand-held power tool 100 can be designed as a screwdriver. Possible operating states A, B, C can describe a screw depth of a screw to be screwed in, screwing in a specific screwing mode (impact mode, screwing in / out), work efficiency, a defined torque, a choice of the screw used, or kickback at high torques.

[0136] Furthermore, the handheld power tool 100 can be configured as a drill. Operating states A, B, C can describe a drilling mode (percussion drilling, etc.), an orientation of the handheld power tool 100 relative to a surface of a workpiece to be machined, a type of insert tool (metal, wood, or stone drill), a drilling depth, an orientation of the handheld power tool 100 relative to a predetermined drilling location, a drilling of cables or pipes, a knockout of a drilled hole, the occurrence of drilling dust, or a kickback when the handheld power tool 100 is suddenly tightened.

[0137] Furthermore, the handheld power tool 100 can be configured as a percussion drill or a hammer drill. Operating states A, B, and C can describe an operating mode, work progress, a risk of damage, vibrations, and noise, or a lack of contact pressure.

[0138] Furthermore, the handheld power tool 100 can be designed as a chisel. Possible operating states A, B, C can describe an incorrectly inserted tool, an effective position of the handheld power tool 100, or a work progress.

[0139] Furthermore, regardless of the design of the handheld power tool 100, possible operating states A, B, C can include aspects of occupational safety / comfort such as vibration / noise development, vibration monitoring, torque control with regard to maximum torques, simple control of the handheld power tool 100, correct clamping of a tool in the handheld power tool 100, or recognition of situations such as falling from a ladder, drilling into cables or pipes. By appropriately training an artificial intelligence of the state determination module 107, the stated operating states A, B, C or similar operating states that can occur during operation of a handheld power tool 100 can be determined based on measured values ​​121 of an operating variable 119 during operation of the handheld power tool 100.

[0140] The operating variable 119 can include, for example, the motor current I or a motor position angle, a motor rotational speed, a voltage of a voltage source, movements and / or vibrations within the hand-held power tool (100) or similar measurable parameters of the hand-held power tool 100.

[0141] Fig. 4 shows a schematic representation of a hand-held power tool 100 according to an embodiment, wherein the hand-held power tool 100 is shown in different operating states A, B, C.

[0142] Fig. 4 graphically describes the operating states A, B, and C of the handheld power tool 100 described in Fig. 3. The handheld power tool 100 is again designed as a screwdriver, and the operating states A, B, and C describe the screwing process in which a screw 169 is screwed into a workpiece 137. The screw 169 can, for example, be a self-tapping screw, and the workpiece 137 can be made of wood. The handheld power tool 100 further comprises a screw bit 168 for this purpose.

[0143] Graphic a) shows the operating state A, in which the screw 169 is screwed into the workpiece 137.

[0144] Graphic b) describes operating state B, which is characterized in that the conical screw head 170 is adjacent to the surface 167 of the workpiece 137 and is subsequently screwed into the workpiece 137. Graphic c) describes operating state C, which is characterized in that the screw 169 is flush with the surface 167 of the workpiece 137, thus reaching the flush point.

[0145] As described above, graph a) of Figure 3 shows the time course of the motor current of the motor 101 of the hand-held power tool 100 in the various operating states A, B, C during the screwing of the screw 169 into the workpiece 137.

[0146] In operating condition A, in which the screw 169 is screwed evenly into the workpiece 137, the motor current I shows a largely horizontal curve, which has a slight gradient with increasing screw-in depth.

[0147] In operating state B, which is characterized by the conical screw head 170 being in contact with the surface 167 of the workpiece 137 and the screwing of the screw head 170 into the workpiece 137, the motor current I shows a steep increase, which is caused by the increased torque required to screw the conical screw head 170 into the workpiece 137.

[0148] The operating state C, which is characterized by the closure of the screw head 170 with the surface 167, shows in graph 3 a flattening course of the motor current I, which can be caused by the destruction of the screw or a destruction of the workpiece 137.

[0149] In Figure 4, the handheld power tool 100 further comprises an external sensor 171. In the embodiment shown, the external sensor 171 is designed as a camera sensor and enables the recording of camera data by means of which the screwing process of screwing the screw 169 into the workpiece 137 can be mapped. The corresponding camera data can be used, as will be described in more detail in the following figures, for training the state determination module 107 or an artificial intelligence 149 of the state determination module 107. Figure 5 shows a schematic representation of a drive control 197 of the handheld power tool 100 according to one embodiment.

[0150] Fig. 5 shows a control chain of the hand-held power tool 100.

[0151] According to the invention, the control chain comprises an inner control loop 193 and an outer control loop 191. The inner control loop 193 serves to control the drive of the handheld power tool 100 based on the user inputs 173 of the user.

[0152] To control the drive of the handheld power tool 100 based on the user inputs 173 of the user by exclusively the inner control loop 193, user inputs 173 are first provided by the user. This can be done, for example, by actuating the trigger switch 109. This can be used to define initial target values ​​of a control parameter of the handheld power tool 100 through the user input. The control parameter can include, for example, a motor speed, a motor power, or a torque defined by the motor speed. Alternatively, the control parameter can include a direction of rotation, such as when screwing in or unscrewing a screw, or an operating mode, such as impact mode or hammer mode. The user inputs 173 describe values ​​of the control parameter.

[0153] Actual values ​​of the control parameter are recorded via sensor measurements 175 of an operating variable 119, which describe an actual state of the actuator 195 of a drive control 197 of the hand-held power tool 100.

[0154] The sensor measurements 175 of the operating variable 119 can include measurements of the motor current, the motor speed, the motor power, vibrations of the motor or the handheld power tool 100, or other meaningful operating variables that enable the determination of an operating state A, B, C. The first target values ​​of the user inputs 173 and the actual values ​​of the sensor measurements 175 of the control parameter are transmitted to the inner control loop 193 by performing digital signal preprocessing 177.

[0155] The inner control circuit 193 outputs corresponding control signals to the actuators 195 for controlling the hand-held power tool 100.

[0156] The outer control loop 191 is now used to take into account an operating state A, B, C in which the hand-held power tool 100 is during operation when controlling the hand-held power tool 100.

[0157] For this purpose, the first target values ​​of the control parameter of the user input 173 and in particular the actual values ​​of the sensor measurements 175 of the control parameter are subjected to a model inference 183 after digital signal preprocessing 197. In the model inference 183, the previously described embodiment of the state determination module 107 takes effect. The state determination module 107 is configured to recognize an operating state A, B, C in which the handheld power tool 100 is located based on the sensor measurements 175 or the corresponding sensor data of the control parameter. Alternatively or additionally, the state determination module 107 can be configured to predict an event time 125, 126 at which a transition between different operating states A, B, C of the handheld power tool 100 occurs based on the sensor data of the sensor measurements 175 of the operating variable 119.

[0158] The state determination module 107 implemented in the model inference 183 can be embodied as a correspondingly trained artificial intelligence that is trained to determine operating states A, B, C or to predict event times 125, 126 based on measured values ​​of an operating variable 119. The information determined by the state determination module 107 in the form of the model inference 183 regarding the present operating states A, B, C or predicted event times 125, 126 is provided to the outer control loop 191 after post-processing 187.

[0159] The outer control loop 191 is then configured to define corresponding second target values ​​for the control parameter based on the information from the model inference 183 regarding the current operating states A, B, C or the predicted event times 125, 126. The second target values ​​for the control parameter defined by the outer control loop 191 are coordinated with the respective current operating state A, B, C or the corresponding predicted event times 125, 126. Taking into account the second target value of the control parameter generated by the outer control loop 191, the control of the handheld power tool 100 can be optimally adapted to the respective current operating state A, B, C or the corresponding predicted event times 125, 126.

[0160] The second target value for the control parameter generated by the control loop 191 is subsequently provided to the inner control loop 193.

[0161] According to the invention, the inner control loop 193 is now configured to calculate an output target value taking into account the first target value for the control parameter provided by the user in the user input 173 and the further second target value for the control parameter provided by the outer control loop 191 taking into account the present operating state A, B, C or the predicted event time 125, 126, and to control the actuator 195 of the handheld power tool 100 based on the output target value.

[0162] The output target value can be calculated by the inner control loop 193, for example, as a product of the first target value of the user input 173 and the second target value of the outer control loop 191. Through the product of the first and second target values, the first target value of the user input 173 can thus be sensitized by the second target value of the outer control loop 191, which was determined with reference to the current operating state A, B, C or the predicted event time 125, 126, i.e., adapted to the respective operating state A, B, C or the expected event time 125, 126. Alternatively, the output target value can be defined as a minimum or maximum value of the first and second target values. This allows the output target to be defined as the value of the first and second target values ​​that best fits the respectively determined operating state A, B, C.

[0163] Alternatively, the output target value can be defined by the first target value of the useful input 173 if the second target value of the outer control loop 191 is less than a predefined threshold value, and can be defined as a predefined target value if the second target value is greater than or equal to the predefined threshold value. The predefined target value can be given as a constant value of the control parameter, which, for example, was adjusted during a presetting of the hand-held power tool 100 to the respective existing operating state A, B, C or a preceding event time 125, 126. The predefined threshold value can, for example, be empirically adjusted through appropriate measurements to the respective occurring operating states A, B, C and possible second target values.

[0164] Alternatively, the output target value can be defined as a product of the first target value of the user input 173 with a first predefined target value if the second target value of the outer control loop 191 is less than a predefined threshold, and as a product of the first target value of the user input 173 and a second predefined target value if the second target value of the outer control loop 191 is greater than or equal to the predefined threshold. Depending on the second target value determined by the outer control loop 191, the first target value of the user input 173 can thus be sensitized or adapted to the respective existing operating state A, B, C or the expected event time 125, 126 in the form of the first and second predefined target values, which can each be defined as constant values ​​of the control parameter and adapted to the respective existing operating states or expected event times.The first and second predefined target values ​​and predefined threshold values ​​can in turn be determined empirically for possible operating states A, B, C.

[0165] In the form of the output target value determined by the inner control loop 193, the handheld power tool 100 can thus be controlled taking into account the user input 173 made by the user of the handheld power tool 100 and the corresponding first target value of the control parameter and taking into account the second target value of the control parameter determined with respect to the present operating state A, B, C or the expected event time 125, 126.

[0166] In the embodiment of Figures 3 and 4, in which the hand-held power tool 100 is designed as a screwdriver, and in which a screwing case is described in which a self-tapping screw 169 is screwed into a wooden workpiece 137, and in which the different operating states A, B, C describe the screwing of the screw 169 into the workpiece 137 in operating state A, the screwing of the conical screw head 170 into the workpiece 137 in operating state B and the flush closure of the screw head 170 with the surface 167 of the workpiece 137 in operating state C, the control parameter can be, for example, a rotational speed of the motor 101 of the hand-held power tool 100.

[0167] The user input 173 may, for example, include signals from the trigger switch 109 actuated by the user, by means of which the respective first target value of the engine speed is defined.

[0168] The operating variable 119 determined in the sensor measurements 175 can be given, for example, by the motor current I of the motor 101 of the handheld power tool 100. The state determination module 107, which is applied to the measured values ​​of the motor current I according to the model inference 183, can be configured accordingly to determine the various operating states A, B, C based on the motor current I, according to graph A of Figure 3. Furthermore, the state determination module 107 can be configured to predict the respective event times 125, 126 based on the measured values ​​121.

[0169] In the following, the processes described above and in particular the determination of the second target value by the outer control loop 191 or the determination of the output target value by the inner control loop 193 are described for an application in which, according to the embodiments of Figs. 3 and 4, the hand-held power tool 100 is designed as a screwdriver and a screw 169 is screwed into a workpiece 137 by means of this.

[0170] The user input 173 based on the actuation of the trigger switch 109 can, for example, define a correspondingly high value for the motor speed as the first target value. Based on the sensor measurements 175 of the motor current, the state determination module 107 determines, however, that the handheld power tool 100 is already in operating state C of Figure 3, in which the flush point has already been reached and the screw head 170 is flush with the surface 167 of the workpiece 137. Based on this, the outer control loop 191 calculates a significantly lower value for the motor speed as the second target value in order to prevent damage to the screw or the workpiece 137, which would be feared at the high motor speed of the user input 173.By determining the output target value by the inner control loop 193, the obviously too high target value for the motor speed of the user input 173 can be reduced by the significantly lower second target value for the motor speed calculated by the outer control loop 191, in order to thus control the hand-held power tool 100 according to the present operating state C and, if necessary, to switch it off.

[0171] For this purpose, the second target value as well as the first and second predefined

[0172] Target values ​​take the numerical value 0. The output target value can also be reduced to the numerical value 0, which can bring the hand-held power tool 100 to a standstill.

[0173] In the embodiment shown, the model inference information 183 may further be displayed in a status display 189.

[0174] Furthermore, the model inference can be subjected to a reset process in which the model executions are reset to an initial value. This can be done, for example, during separate screwing processes. For example, the state determination module 107 can be reset for each new screwing process in which an individual screw is screwed into or unscrewed from a workpiece 137. Alternatively or additionally, a reset can also be performed when the handheld power tool 100 is switched on or off.

[0175] For this purpose, a reset preprocessing 181 is first performed based on the sensor measurements 175, and a reset decision 185 is made based on this. The reset decision 185 can also be made taking into account the results of the model inference 183.

[0176] The information from model inference 183 and post-processing 187 can be provided in digital or quasi-analog form.

[0177] Fig. 6 shows a flowchart of a method 200 for controlling a handheld power tool 100 according to an embodiment.

[0178] To control the handheld power tool 100, in a first method step 201, sensor data of at least one operating variable 119 of the handheld power tool 100 is first received. The operating variable 119 can, for example, comprise a motor current, a motor position angle, a motor rotational speed, a voltage of a voltage source, measured values ​​of a movement or vibration of the handheld power tool 100, or similar parameters from which an operating state A, B, C of the handheld power tool 100 can be determined. In a further method step 203, based on this, an input value for a control parameter of the handheld power tool 100 is received, which is based on a user input 173 from a user of the handheld power tool 100. The control parameter can, for example, comprise a motor speed, a motor current, a motor power, an actuation of the trigger switch 109, an input regarding an operating mode, for example switching on or off.Switching on the impact mode or chisel mode, a direction of rotation of the motor 101, for example for screwing in or unscrewing a screw 169, or similar control parameters.

[0179] In a further method step 205, a first target value of the control parameter is determined based on the sensor data of the operating variable 119 and the input value of the user input 173 regarding the control parameter.

[0180] In a further method step 207, a state determination module 107 is executed and applied to the sensor data of the operating variable 119. By executing the state determination module 107, an operating state A, B, C of the handheld power tool 100 is determined. Determining the operating state can include predicting an event time 125, 126 at which a transition between two operating states A, B, C occurs.The operating states A, B, C can include load ranges in which the handheld power tool 100 is operated, intensities of vibrations or movements of the handheld power tool 100 and / or the workpiece 167 to be machined, temperatures within the handheld power tool 100 and / or on the workpiece 167, various operating modes in which the handheld power tool 100 is operated, work progress of the handheld power tool 100, materials of the workpiece 137 to be machined, or, for example, the already described presence of a positive connection between the handheld power tool 100 and the machined workpiece 137, in which a screw head 170 of a screw 169 to be screwed in is flush with a surface 167 of the workpiece 137. Alternatively, other and additional operating states of the handheld power tool 100 are conceivable, which can be detected via the analysis of the measurable operating variables 119 of the handheld power tool 100.

[0181] In a further method step 209, control of the handheld power tool 100 is effected based on the first target value of the user input 173 and taking into account the determined operating state A, B, C in which the handheld power tool 100 is located. As already described above, the first target value of the control parameter of the user input 173 can be adapted to the current operating state A, B, C in order to achieve control adapted to the respective current operating state A, B, C.

[0182] The control 209 may include, for example, adjusting an engine speed, an engine torque or another control parameter.

[0183] Fig. 7 shows a further flowchart of the method 200 for controlling a hand-held power tool 100 according to a further embodiment.

[0184] The embodiment in Fig. 7 is based on the embodiment in Fig. 6 and the method 100 includes all method steps shown there.

[0185] In the embodiment shown, a method step 211 is first carried out to control 209 the hand-held power tool 100.

[0186] In method step 211, a second target value of the control parameter is determined based on the determined operating state A, B, C or predicted event time 125, 126 of the handheld power tool 100. As described for Fig. 5, the determination of the second target value can be carried out by the outer control loop 191. The determination of the second target value can comprise a calculation of the second target value, in which a corresponding second target value is calculated during execution and upon detection of the respective existing operating state A, B, C or upon prediction of the expected event time 125, 126. Alternatively, the determination can comprise reading a corresponding second target value from a look-up table in which suitable second target values ​​are pre-stored for various possible operating states A, B, C or predicted event times 125, 126.Alternatively, the state determination module 107 can also be configured to determine appropriately adjusted second target values ​​of the control parameter based on the determined operating state A, B, C.

[0187] In a further method step 213, an output target value of the control parameter is determined based on the first target value and the second target value. As already explained with reference to Fig. 5, the determination of the output target value is effected by the inner control loop 193. The determination can in turn comprise calculating a corresponding output target value based on the first and second target values. Alternatively, a corresponding output target value can be read from a look-up table prestored for this purpose. Alternatively, the state determination module 107 can in turn be configured to determine the output target value of the control parameter based on the first and second target values.

[0188] In a further method step 213, the output target value is output to an actuator 195 of the drive control 197 of the handheld power tool 100 for controlling the handheld power tool 100.

[0189] Fig. 8 shows a further flowchart of the method 200 for controlling a hand-held power tool 100 according to a further embodiment.

[0190] The embodiment shown is based on the embodiment in Fig. 7 and includes all method steps described there.

[0191] In the embodiment shown, determining 207 the operating state A, B, C further comprises predicting 225 an event time 125, 126 at which a transition occurs between different operating states A, B, C. Furthermore, determining 213 the output target value comprises a method step 217. In method step 225, the output target value is defined as a minimum value or a maximum value of the first and second target values.

[0192] Furthermore, method step 213 includes method step 219. In method step 219, the output target value is defined as the first target value if the second target value is less than a predefined threshold. If the second target value is greater than or equal to the predefined threshold, the output target value is defined as a predefined target value.

[0193] In a method step 221, the output target value is defined as a product between the first and second target values.

[0194] In a method step 223, the output target value is defined as a product between the first target value and a first predefined target value if the second target value is less than a predefined threshold. If the second target value is greater than or equal to the predefined threshold, the output target value is defined as a product between the first target value and a second predefined target value.

[0195] The predefined target values ​​can be configured as constant values ​​of the control parameter and can be pre-stored. The corresponding threshold values ​​can also be pre-stored. The defined target values ​​as well as the predefined threshold values ​​can be optimized for optimized operation of the hand-held power tool 100 for the respective existing operating states A, B, C or preceding event times 125, 126.

[0196] As already explained in relation to Fig. 5, the determination 213 of the output target value in the embodiment shown is effected by the inner control loop 193. The predefined target values ​​as well as the second target value, which is determined by the outer control loop 191, can assume the numerical value 0. This can cause the hand-held power tool 100 to be switched off, depending on the selection of the control parameter. By taking into account the predefined target values ​​or the second target value according to the described method steps 215 to 221, the first target value of the control parameter, which is based on the user input 173 by the user, can be adapted to the respective existing operating state A, B, C or the expected event time 125, 126.

[0197] Fig. 9 shows a schematic representation of an artificial intelligence 149 which is configured to be used in a control system of the hand-held power tool 100.

[0198] The state determination module 107 can comprise a correspondingly trained artificial intelligence 149, which is trained to determine existing operating states A, B, C or to predict event times 125, 126 based on measured values ​​of the operating variable 119. The state determination module 107 can further be configured to determine second target values ​​or output target values.

[0199] Fig. 9 shows an embodiment of such an artificial intelligence 149, which can be used to determine operating states A, B, C or to predict event times 125, 126.

[0200] In the embodiment shown, the artificial intelligence 149 is designed as an artificial neural network and in particular as a long-short-term memory LSTM network.

[0201] In the embodiment shown, the artificial neural network comprises an input layer 153 for receiving input data 151. The input data may comprise the sensor data of the operating variable 119 in a correspondingly preprocessed form.

[0202] The artificial neural network further comprises two dense layers 155 and two pooling layers 157, which are arranged one after the other in an alternating fashion. Furthermore, the artificial neural network comprises two long-short-term memory layers 159, between which a dropout layer 161 is arranged. Finally, the artificial neural network further comprises two dense layers and an output layer 163.

[0203] In data processing, downsampling 164 is initially performed by the input layer 153, the first two dense layers 155, and the two pooling layers 157. The two following LSTM layers 159 and the intermediate dropout layer 161 perform feature extraction 165. The last two dense layers 155 and the output layer 163 enable prediction 166.

[0204] Deviating from the embodiment shown, the artificial intelligence 149 used can also be structured in a different model architecture capable of performing a regression or classification based on a time series 123 of measured values ​​121 of the operating variable 119. However, a prerequisite for the model architecture used for the artificial intelligence 149 is that the respective model can be provided in a format that can be executed on a microcontroller of a handheld power tool 100.

[0205] For the implementation described here, a Tensorflow / Keras model with the architecture shown below can be used. After training, the model can first be converted to Tensorflow Lite format, which can then be translated into C code for the microcontroller using a TVM converter.

[0206] The three input channels can be, for example, the motor current I of the motor 101, the trigger voltage of the trigger switch 109 and the motor revolutions per second.

[0207] The architecture used can be structured as follows:

[0208]

[0209] Absolute number of parameters used: 7,801

[0210] Of which trainable parameters: 7,801 non-trainable parameters: 0

[0211] The first dense layer 155 can be configured with a 6x8 kernel and an 8 bias. The second dense layer 155 can be configured with an 8x16 kernel and a 16 bias. The first LSTM layer 159 can be configured with a 16x128 kernel, a 32x128 recurrent kernel, and a 128 bias. The second LSTM layer 159 can be configured with a 32x32 kernel, an 8x32 recurrent kernel, and a 32 bias. The third dense layer 155 can be configured with an 8x4 kernel and a 4 bias. The fourth dense layer 155 can be configured with a 4x1 kernel and a 1 bias.

[0212] The dense layer 155 and the LSTM layer 159 can be designed with a TanH activation function.

[0213] Fig. 10 shows a flowchart of a method 300 for generating a training data set for training an artificial intelligence 149 according to one embodiment.

[0214] To train the artificial intelligence 149, a training data set is first generated according to the invention. For this purpose, according to the method 300 according to the invention, in a method step 301, a plurality of measured values ​​121 of the operating variable 119 of the handheld power tool 100 are first provided. The measured values ​​121 each have time stamps that define the times at which the measured values ​​121 were recorded. The measured values ​​121 can be recorded during the operation of the handheld power tool 100. Alternatively, the measured values ​​121 can be recorded during the operation of a plurality of different handheld power tools 100 of the same type. The measured values ​​121 of the operating variable 123 can be recorded by the plurality of different handheld power tools 100 and transmitted, for example, to a server architecture provided for generating a training data set.This can carry out appropriate processing and archiving of the measurement data in order to generate a corresponding training data set based on this.

[0215] For this purpose, in a further method step 303, an event time 125 is identified within the plurality of measurement data 121 at which an operating state transition occurs between two operating states A, B, C. The identification of the event time 125 is carried out based on the time stamps of the individual measured values ​​121.

[0216] In a further method step 305, the measured values ​​121 are provided with label values ​​suitable for assigning the respective measured value to an operating state A, B, C or for identifying it with the respective event time 125, 126. The label values ​​can be assigned, for example, using algorithms for labeling training data for artificial intelligence 149 that are provided for this purpose and are known from the prior art. Alternatively, the measured values ​​121 can be labeled manually by appropriately trained personnel. Alternatively, the measured values ​​automatically labeled by the algorithm can be checked by appropriately trained personnel for correct and error-free labeling.

[0217] In a further method step 307, the labeled measured values ​​121 of the operating variable 119 are arranged in a time series 123. This is done based on the timestamps. The time series 123 describes a temporal arrangement of the labeled measured values ​​121 according to the timestamps.

[0218] After method step 307 and before a further method step 309, a consolidation of the majority of existing labels can be performed. This can be done, in particular, based on statistical criteria. For example, by calculating a median of the event time from multiple manual and automatic sources, a more robust label for the actual event time can be created, thereby achieving greater accuracy of the time label.

[0219] In the further method step 309, the time series 123 of the labeled measured values ​​121 of the operating variable 119 is provided as a corresponding training data set.

[0220] Fig. 11 shows a further flowchart of a method 300 for generating a training data set for training an artificial intelligence 149 according to a further embodiment.

[0221] The embodiment shown is based on the embodiment in Fig. 10 and includes all method steps described there.

[0222] In the embodiment shown, first in a method step 211 for each measured value 121 of the operating variable 119 a rotation angle a ro t of the motor 101 of the hand-held power tool 100 is determined. For this purpose, the rotation angles a ro t of the motor 101 and assigned to the measured values ​​121 based on the time stamps. The rotation angles a rot of the motor 101 describes the angle of rotation that the motor 101 had at the time the respective measured value 121 of the operating variable 119 was recorded.

[0223] In a further method step 313, a rotation time t ro t is calculated for each measured value 121 of the operating variable 119, taking into account the time required to complete one revolution of the motor 101 and the time stamp of the respective measured value 121. The rotation time t ro t describes the point in time at which, starting from the angle of rotation a ro t of the respective measured value 121 a complete revolution of the motor 101 has occurred.

[0224] In the embodiment shown, identifying 303 the event time 125, 126 further comprises method step 315. In this method step, sensor data from an external sensor 171 is received. The sensor data from the external sensor 171 maps the operating state A, B, C of the handheld power tool 100. The external sensor 171 can be designed, for example, as a camera sensor. Using the camera data from the camera sensor, the operating state A, B, C in which the handheld power tool 100 was at the time the measured values ​​121 of the operating variable 119 were recorded can be mapped. As shown in Fig. 4, the work progress of the process of screwing the screw 169 into the workpiece 137 can be mapped or tracked via the camera sensor 171, which is designed, for example, on the handheld power tool 100.

[0225] In a further method step 317, the event time 125, 126 is determined within a time series of the sensor data from the external sensor 171. For this purpose, the sensor data from the external sensor 171 are arranged in a time series according to their time stamps. By analyzing the image data from the camera sensor, the exact time can be identified at which, for example, the flat connection of the screw head 170 with the surface 167 of the workpiece 137 occurred, as indicated in Figure 4 in operating state C. Using the corresponding time stamps of the recorded image data from the camera sensor 171, the exact time of the event time 125 can be determined within the time series of the image data, at which the transition between the operating states B and C shown in Figure 4 occurred and thus the flat connection between the screw head 170 of the screw 169 and the surface 167 of the workpiece 137 is reached.In a further method step 319, the time series 123 of the measured values ​​121 of the operating variable 119 is synchronized with the time series 123 of the sensor data of the external sensor 171 via the respective time stamps of the measured values ​​121 or the sensor data of the external sensor 171.

[0226] In a further method step 321, the event time 125, 126 in the time range 123 of the measured values ​​121 of the operating variable 119 is identified based on the event time 125, 126 identified in the time series of the sensor data of the external sensor 171. By synchronizing the time series 123 of the measured values ​​121 of the operating variable 119, which is given, for example, by the motor current I of the motor 101, and the time range of the sensor data of the external sensor 171, each measured value 121 of the operating variable 119 can be assigned a simultaneously recorded image datum or sensor datum of the external camera sensor 171.

[0227] By inspecting or analyzing the image data of the external camera sensor 171, for example by appropriately trained personnel, the various operating states A, B, C or the various event times 125, 126, which are described, for example, in Fig. 4 by the screwing of the screw 169 into the workpiece 137, the screwing of the screw head 170 into the workpiece 137 and the leveling of the conical screw head 170 with the surface 167 of the workpiece 137, can be precisely determined. As a result of the synchronization of the two time series, namely the time series 123 of the measured values ​​121 of the operating variable 119 and the time series of the sensor values ​​of the external sensor 171, each measured value 121 can be assigned to an operating state of the hand-held power tool 100.

[0228] By comparing the image data from the external camera sensor 171, in which the various operating states of the handheld power tool 100 can be easily identified by appropriately trained personnel, and by synchronizing the two time series, the measured values ​​121 of the operating variable 119 can be precisely assigned to the various operating states A, B, C. By taking into account the sensor data from the external sensor 171, the measured values ​​121 of the operating variable 119 can thus be precisely labeled and assigned to clearly defined operating states via the corresponding labels. This can be done in particular for operating variables 119 whose course does not clearly reveal the various operating states A, B, C or the present event times 125, 126.

[0229] Thus, by taking into account the image data of the external camera sensor 171 of the embodiment in Fig. 4, the different operating states A, B, C and the present event times 125, 126 can be determined exactly from the measured values ​​121 of the time range 123 of the course of the motor current I of the graph A of Figure 3, the respective course of the motor current I shown in graph A of Figure 3 does not explicitly represent such different operating states A, B, C or event times 125, 126.

[0230] As an alternative to the described process steps, further steps can be performed to generate the training data set. For example, the recorded measured values ​​121 of the operating variable 119 or the sensor data of the external sensor 171 can be converted into standard units. Furthermore, the measured values ​​of the angle of rotation a ro t are pre-cleaned. Especially if the measured values ​​of the rotation angle a rot were recorded via Hall sensors, the possibility of an overflow of the Hall sensor data can be taken into account with regard to the data type Unit 16 used.

[0231] In particular, recorded angles of rotation a rot, for which an overflow can occur due to continuous operation and data type, can be corrected to a continuous value range. This can advantageously be achieved by shifting the angle values ​​to the initial value zero, whereby the angle of rotation reflects the angular progress compared to the starting point (e.g., the screwing-in process) at any time. Furthermore, the time series 123 of the measured values ​​121 of the operating variable 119 as well as the time series of the sensor data of the external sensor 171 can be shortened to the time ranges in which the hand-held power tool 100 is actually operated. According to the embodiment shown in Fig. 4, the time series can be limited to the actual screwing case in which the screw 169 is actually screwed into the workpiece 137.Measurement values ​​recorded before the start of the tightening process and after the end of the tightening process can be removed from the time series. Alternatively, all data before or after a specified time before or after the labeled event time 125, 126 can be removed to shorten the time series 123 and reduce the data volume.

[0232] Furthermore, the acquisition rate of the measured values ​​or sensor data can be scaled down. Furthermore, the recorded measured values ​​or sensor data can be filtered.

[0233] Furthermore, feature extraction can be performed to obtain derived sensor signals, such as acceleration vector lengths, angular rate vector lengths from a gyroscope, motor revolutions per second.

[0234] Furthermore, as is common in machine learning, the training dataset can be divided into training data and validation or test data. The division can be as follows, for example: 70% training data, 20% test data, and 10% validation data.

[0235] When dividing the data into training, validation and test data, a so-called stratified split can be performed.

[0236] However, to demonstrate the generalization of the function across typical operating ranges, a different split can be advantageously used, particularly by using only certain operating ranges for training and others for validation or testing. In this case, the achievement of the desired generalization is indicated by the fact that the accuracy of the function on the test dataset is only slightly worse than the accuracy of the function in the test dataset with a stratified split. Suitable operating parameters include, in particular, screw lengths, speed, screw diameter, type and hardness of the wood, and other application parameters.

[0237] Furthermore, normalization parameters can be calculated. For example, a min-max scaling method (parameters per signal: minimum, maximum) or a standardization method (parameters per signal: mean and standard deviation) can be used. The parameters can be calculated exclusively based on the training dataset. It is important to ensure that the normalization parameters are not distorted by the selected padding.

[0238] Since the respective time series 123 may have different lengths depending on the operation of the handheld power tool 100, for example, the screwing process described in the embodiments of Figures 3 and 4, since screwing processes of different lengths were performed, the training data can be condensed to a uniform length. This is necessary because the input data of the artificial intelligence must have a uniform data format. It can also be considered whether the data padded in this way contains a 0 in all signals or whether they represent a copy of the first (start padding) or last (end padding) real data.

[0239] In the neural network architecture described in Figure 9, due to the network architecture used, in which effective downsampling occurs within the network through the pooling layers, padding is also used to ensure that all time series data are divisible by the total pooling factor Fp, which results from the product of the individual pooling factors in the network. This ensures that each group of Fp samples has a unique assignment of a label of the output value. In the suitable network architecture shown, Fp=16 results from the pooling layers.

[0240] The test data set, however, can be used unpadded, although typically no result can be calculated for the last samples.

[0241] Alternatively, augmentation techniques can be used to generate new data that essentially correspond to real data. For example, new time series of data from farm size 119 can be generated.

[0242] Finally, a normalization can be performed based on the previously calculated normalization parameters (standardization or mini-max scaling).

[0243] In addition to being designed as a camera sensor, the external sensor 271 can also be configured as a microphone, for example. Multiple external sensors can also be used.

[0244] Data acquisition can be recorded on various devices, such as a microcontroller and a Raspberry Pi. The data from both the operating variable 119 and the data from the external sensor on the handheld power tool 100 can be recorded and transferred to the external server architecture. Due to the different sampling rates between the various sensors 171 and the sensors for acquiring the operating variable 119, preprocessing of the acquired data may be necessary. In particular, metadata can be checked during this process.

[0245] The labeling of the measured values ​​121 can be implemented as an event label, in which each measured value 121 is assigned a corresponding time. Alternatively or additionally, a state label can be implemented, in which each measured value 121 is assigned a corresponding time range. Furthermore, the measured values ​​121 of the operating variable 119 and / or the sensor data of the external sensor 171 can be subjected to a sanity check, in which the accuracy of the respective data is verified.

[0246] Fig. 12 shows a flowchart of a method 400 for training an artificial intelligence 149.

[0247] To train the artificial intelligence 149 according to the inventive method 400 for training an artificial intelligence 149 for determining an operating state A, B, C of a hand-held power tool 100, a training data set generated according to the method 300 according to one of the embodiments described above is first provided in a method step 401.

[0248] In a method step 403, the training of the artificial intelligence 149 is carried out to determine an operating state A, B, C and / or to predict an event time 125, 126 of a handheld power tool 100 based on the training data set. The training can be carried out according to training methods known from the prior art.

[0249] Experimentally, a batch size of 16 has proven advantageous for training the artificial intelligence model architecture of the embodiment described in Figure 9. As an optimization algorithm, the Adam algorithm can produce satisfactory results. Specifically for the application discussed here, a relatively low learning rate of 0.0001 is sufficient. As a result, a comparatively high number of training epochs is required. Typically, no upper limit for the number of epochs needs to be defined in advance, and training can only be terminated when the validation dataset determines that no further improvement in the model can be achieved over a longer period of time (so-called early stopping). In a training setting advantageous for the application discussed here, this "longer period" is defined as 300 epochs.

[0250] However, during development, it has been repeatedly observed that training runs for the selected learning rate are stopped relatively early (approximately after less than 2000 epochs), and corresponding models perform significantly worse than models trained over more epochs. Early stopping is extended to allow a minimum number of epochs to be defined. Subsequently, a minimum of 2000 or 1500 epochs is typically configured. The mean squared error (MSE) is used as the loss function.

[0251] Typically, it is advantageous to begin training with a portion of the time series data before using the entire time series. In particular, the range around a critical point (e.g., the point to be detected) can be used to train the rough behavior of the model. Only in a subsequent step (after, for example, 10%-50% of the total training epochs) is the entire time series used to train the model behavior in the more distant temporal ranges.

[0252] This approach is particularly advantageous because it reduces the likelihood of obtaining a suboptimal training result. For typical applications involving screwdrivers and drills, a range of 0.1 s to 10 s before and after the event time can be used, with 0.5 s proving particularly suitable for the application discussed here.

[0253] To assess model quality after training, an automated theoretical evaluation is first performed based on a test dataset. The test dataset undergoes the same preprocessing steps that are performed on the microcontroller during inference. These include, as described above, conversion to SI units, calculation of revolutions per second based on the Hall sensor signal, and normalization based on the normalization parameters determined from the training dataset.

[0254] During the evaluation, this data, which corresponds to the data from live use, is fed into the model to analyze the model's behavior. Since the activation function of the output neuron is defined as the hyperbolic tangent (tanh), the outputs lie within the value range [-1, 1]. The trigger time is considered the time within the prediction time series at which a set threshold is first exceeded. This can be 0, but also closer to -1 or 1, in order to adjust the trigger sensitivity.

[0255] The threshold adjustment can either be set prior to delivery (advantage: consistent behavior) or kept adaptable in the application, e.g., using a control knob. This has the advantage of allowing a more appropriate behavior to be selected for different situations. A typical fixed threshold is between 0 and -1, which achieves earlier triggering and compensates for delays caused by processing and machine inertia. -0.85 has proven to be a particularly suitable value for achieving increased sensitivity while still maintaining an acceptable probability of false triggering.

[0256] For the embodiment described in Figures 3 and 4, two application-specific metrics are primarily used, which also consider each material-screw combination separately. These are:

[0257] The average absolute deviation of the trigger time from the desired (=labeled) trigger time, measured in engine revolutions. Furthermore, the relative deviation from the desired trigger time is also considered in the form of a frequency distribution, as this makes it clear whether the model tends to trigger too early or too late, or whether the modal value is 0 (as desired). The number or proportion of screw connections in which the model did not trigger at any time.

[0258] The loss's MSE plays a minor role, since for real-world applications, the precise prediction for the entire time series is less important than the timing of the trigger. However, it has been shown that the MSE mostly correlates with application-specific metrics.

[0259] For a hand-held power tool 100 designed as a screwdriver, a plurality of combinations of a screw type of the screw 169 and a material type of the respective workpiece 137 can be taken into account for the training of the artificial intelligence 149 of the state determination module 107.

[0260] Various parameters can be considered that influence the quality of the artificial intelligence 149 training and its subsequent performance in determining operating conditions. These include, in particular, the material (e.g., type of wood), the length / diameter / pitch / thread type of the screw, the speed of screwing, and user influences such as tilting and applied pressure. Since it is practically impossible to record data for every conceivable combination, let alone in sufficient quantities, it is advantageous to use selected combinations of different common screw types with a selection of materials of varying hardness. Information about the screw-material combination used can be stored in the form of metadata and used in training. In general, care must be taken to ensure that a sufficient number of recordings (at least 25, preferably more) are made for each combination.It is also advantageous if no combination uses significantly more screw connections than others, ultimately ensuring a balanced data basis for the training. The following provides an example of possible screw-wood combinations for the "screw connection in wood" application case.

[0261] Combinations of various application-relevant wood species (e.g., OSB, pine, beech, spruce) and screw types were used, with typical diameters ranging from 2 mm to 6 mm, lengths from 20 mm to 100 mm, head shapes for Torx or Pozidrive, and with or without self-tapping threads. It is not necessary to maintain records for every gradation and combination of material properties, but a sufficient range of coverage should be available. A number of 100 or more combinations has proven suitable. Particular attention must be paid to avoiding unwanted correlations (e.g., between wood species and screw type) in the records that do not correspond to reality in the application.

[0262] As an alternative to the embodiments described above, the state determination module 107 can also comprise a differently configured artificial intelligence 149 or a plurality of artificial intelligences 149. For example, the state determination module 107 can comprise a differently configured artificial neural network, for example, a temporal convolutional network or a covolutional network. Alternatively, the state determination module 107 can also comprise models such as decision threads or ensemble models.

[0263] The state determination module 107 can be designed and configured, in particular, as a classifier to carry out a classification of the individual measured values ​​121 of the operating variable 119 of the time series 123, to assign the individual measured values ​​121 of the operating variable 119 to corresponding operating states A, B, C, and thereby to determine or predict the event times 125, 126. The measured values ​​121 of the operating variable 119 can be processed by the state determination module 107 according to a sliding window during operation of the hand-held power tool 100 and assigned to corresponding operating states A, B, C according to the classification. According to a sliding window, the time series 123 of the recorded measured values ​​121 are thus analyzed by the state determination module 107, and the operating states A, B, C are thereby determined or the event times 125, 126 are predicted.

[0264] Fig. 13 shows a schematic representation of a computer program product 500, comprising instructions which, when the program is executed by a data processing unit, cause the data processing unit to execute the method 200 for controlling a handheld power tool 100 according to one of the preceding embodiments and / or the method 300 for generating a training data set according to one of the preceding embodiments and / or the method 400 for training an artificial intelligence 149 and / or the artificial intelligence 149. In the embodiment shown, the computer program product 500 is stored on a storage medium 501. The storage medium 501 can be any storage medium known from the prior art.

Claims

Claims 1. A method (200) for controlling a hand-held power tool (100), comprising: Receiving (201) sensor data of at least one operating variable (119) of the hand-held power tool (100); Receiving (203) an input value for a control parameter of the handheld power tool (100) based on a user input from a user of the handheld power tool (100); Determining (205) a first target value of the control parameter based on the sensor data and the input value; Executing (207) a state determination module (107) on the sensor data and determining an operating state (A, B, C) of the hand-held power tool (100); and Controlling (209) the hand-held power tool (100) based on the first target value of the control parameter and the determined operating state (A, B, C).

2. Method (200) according to claim 1, wherein controlling (209) the hand-held power tool (100) comprises: Determining (211) a second target value of the control parameter based on the determined operating state (A, B, C) of the hand-held power tool (100); Determining (213) an output target value of the control parameter based on the first target value and the second target value; and outputting (215) the output target value to an actuator of the handheld power tool (100) for controlling the handheld power tool (100).

3. The method (200) of claim 2, wherein determining (213) the output target value comprises: Defining (217) the output target value as a minimum value or a maximum value of the first and second target values; and / or Defining (219) the output target value as a product of the first and second target values.

4. The method (200) of claim 2 or 3, wherein determining (213) the output target value comprises: Defining (221) the output target value as the first target value if the second target value is less than a predefined threshold, and defining the output target value as a predefined target value if the second target value is greater than or equal to the predefined threshold.

5. The method (200) according to any one of the preceding claims 2 to 4, wherein determining (213) the output target value comprises: Defining (223) the output target value as a product of the first target value with a first predefined target value if the second target value is less than a predefined threshold, and defining the output target value as a product of the first target value with a second predefined target value if the second target value is greater than or equal to the predefined threshold.

6. Method (200) according to one of the preceding claims, wherein determining (207) the operating state (A, B, C) comprises: predicting (225) an event time (125, 126), wherein at the event time (125, 126) a transition of the hand-held power tool (100) from one operating state (A, B, C) to a further operating state (A, B, C) takes place.

7. Method (200) according to one of the preceding claims, wherein the control parameter comprises one or more from the list: motor speed, motor current, motor power of a motor of the hand-held power tool (100).

8. Method (200) according to one of the preceding claims, wherein the operating variable (119) comprises one or more from the list: Motor current, motor position angle, motor rotation speed, voltage of a power source of the hand tool (100).

9. The method (200) according to any one of the preceding claims, wherein the operating state (A, B, C) comprises one or more from the list: a load range in which the handheld power tool (100) is operated, a strength of vibrations in the handheld power tool (100) and / or on a machined workpiece (167) and / or in the user of the handheld power tool (100), a temperature in the handheld power tool (100) and / or on the workpiece (167), an operating mode in which the handheld power tool (100) is operated, a work progress of the handheld power tool (100), material of the workpiece (167), an existence of a positive connection between the handheld power tool (100) and the workpiece (167).

10. The method (200) according to any one of the preceding claims, wherein the state determination module (107) comprises a trained artificial intelligence (149) which is trained to determine the operating state (A, B, C) of the hand-held power tool (100) and / or to predict the event time (125, 126) based on the sensor data of the operating variable.

11. A computing unit (105) configured to execute the method (200) for controlling a hand-held power tool (100) according to one of the preceding claims 1 to 10.

12. Computer program product (500) comprising instructions which, when the program is executed by a data processing unit, cause the data processing unit to carry out the method (200) for controlling a hand-held power tool (100) according to one of the preceding claims 1 to 10.

13. Hand tool (100) with a computing unit (107) according to claim 11 and at least one sensor for determining Sensor data of at least one operating variable of the hand-held power tool (100).

Images