Calibration method and device of force sensor

Abstract

The embodiment of the invention provides a calibration method and device for a force sensor. The method comprises the following steps: acquiring first detection data of continuous external acting force based on a target force sensor; acquiring continuous second detection data of the external acting force based on a standard force sensor, wherein the force sensor and the standard force sensor are arranged on data acquisition equipment and detect the same external acting force; inputting the first detection data into a neural network model, and determining a prediction result; and adjusting the neural network model according to the prediction result and the second detection data, determining a trained neural network model, and calibrating the target force sensor through the trained neural network model. By adopting the scheme, a large amount of continuous external acting force can be obtained, so that a large amount of training data is obtained to train the model, the trained model is more accurate, and the detection accuracy of the force sensor is improved.

Description

Technical Field

[0001] The present application relates to the field of computer information technology, and in particular, to a calibration method and device for a force sensor. Background Art

[0002] A force sensor is a device used to detect the force exerted on an object. It can convert the force exerted on an object into an electrical signal, an optical signal or other forms of signals and output them, so that the magnitude and angle of the applied force can be quantified and recorded. Traditional force sensors mainly include electrical force sensors and optical force sensors. Electrical force sensors convert contact force into corresponding measurable electrical signals through sensitive elements, and obtain contact force information through circuit and software processing. They have the characteristics of high sensitivity, wide measurement range, strong customizability and high real-time performance. Optical force sensors mainly measure contact force based on the principle of optical modulation of optical fibers, and have the characteristics of high accuracy and wide measurement range.

[0003] In reality, since errors are inevitable in the actual manufacturing and assembly process of the force sensor, the force sensor will have deviations to varying degrees. For some delicate scenes, the detection results of the force sensor are inaccurate. Summary of the invention

[0004] The embodiments of the present application provide a method and device for calibrating a force sensor, which can process the collected information of the force sensor to calibrate the force sensor and obtain more accurate detection results.

[0005] The technical solution is as follows:

[0006] In a first aspect, the present application provides a method for calibrating a force sensor, the method comprising: obtaining first detection data of continuous external force based on a target force sensor; obtaining second detection data of continuous external force based on a standard force sensor, the force sensor and the standard force sensor being arranged on a data acquisition device and detecting the same external force; inputting the first detection data into a neural network model to determine a prediction result; adjusting the neural network model according to the prediction result and the second detection data to determine a trained neural network model, so as to calibrate the target force sensor through the trained neural network model.

[0007] Furthermore, the target force sensor is a three-dimensional force sensor, and the neural network model includes: an input layer, used to input the input detection data into a hidden layer, and the detection data is determined based on force detection information in three mutually perpendicular first coordinate directions; a hidden layer, used to analyze the detection data and determine a prediction result; an output layer, used to output a prediction result, and the prediction result includes the force prediction results in the three mutually perpendicular second coordinate directions.

[0008] Furthermore, the neural network model is adjusted based on the prediction result and the second detection data to determine the trained neural network model, including: comparing the prediction result with the second detection data to determine the difference; determining the parameter adjustment amount of the neural network model based on the difference; and reversely adjusting the neural network model according to the parameter adjustment amount.

[0009] Furthermore, the first coordinate direction and the second coordinate direction point to the same direction.

[0010] Furthermore, the first coordinate direction and the second coordinate direction point to at least partially different directions, and the method also includes: obtaining a mapping relationship between the first coordinate direction and the second coordinate direction; and adjusting the detection information of the three-dimensional force sensor or the detection information of the standard force sensor based on the mapping relationship.

[0011] Furthermore, the first coordinate direction and the second coordinate direction point to at least partially different points, and comparing the prediction result with the second detection data includes: obtaining a mapping relationship between the first coordinate direction and the second coordinate direction; adjusting the prediction result or the second detection data based on the mapping relationship, and comparing the adjusted data to determine the difference.

[0012] Furthermore, the data acquisition device includes: a first fixture for fixing the three-dimensional force sensor and a second fixture for installing the first fixture, and the standard force sensor is arranged outside the first fixture.

[0013] Furthermore, the three-dimensional force sensor is composed of an integrated elastic matrix and optical fiber, and the elastic matrix includes a first region, a second region and a third region; wherein the first region and the second region adopt a cantilever beam structure, which are placed crosswise at a 90-degree angle, and the third region is a hollow tubular structure and is engraved with rectangular grooves to form a multi-layer continuous cantilever beam.

[0014] Furthermore, the method also includes: obtaining target detection data of the force sensor to be calibrated for the force to be detected; inputting the target detection data into the trained neural network model to determine calibration data of the force to be detected; and calibrating the force sensor to be calibrated according to the calibration data.

[0015] In a second aspect, the present application provides a calibration device for a force sensor, the device comprising: a first data acquisition module, used to acquire first detection data of continuous external force based on the force sensor; a second data acquisition module, used to acquire second detection data of continuous external force based on a standard force sensor; a prediction result acquisition module, used to input the first detection data into a neural network model to determine a prediction result; and a model training processing module, used to adjust the neural network model according to the prediction result and the second detection data, determine a trained neural network model, and calibrate the target force sensor through the trained neural network model.

[0016] In a third aspect, the present application provides a network device comprising: a memory, a transceiver, and a processor; wherein the memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor is used to read the computer program in the memory and execute the method described in the first aspect or the second aspect.

[0017] In a fourth aspect, the present application provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in the first aspect or the second aspect.

[0018] The beneficial effects of the technical solution provided by this application are:

[0019] The solution of the present application can be applied in the calibration scenario of force sensors. The purpose of the force sensor calibration method is to determine the exact relationship between the sensor output and the applied force to ensure the reliability and accuracy of the measurement results. The specific implementation steps are to apply different contact forces to the force sensor, record the output signal of the corresponding force sensor, and establish a model of the relationship between the contact force and the output signal. For example, this solution can be applied in the calibration scenario of a three-dimensional force sensor. A neural network model can be trained, and the output signal of the three-dimensional force sensor can be calibrated through the neural network model to improve the accuracy of the detection results of the three-dimensional force sensor.

[0020] Specifically, the present solution can be provided with a target force sensor and a standard force sensor for detecting the same external force, the target force sensor can be a three-dimensional force sensor, and the standard force sensor is a pre-calibrated force sensor; the target force sensor and the standard force sensor can obtain first detection data and second detection data by applying continuous external force (such as applying multiple different forces in multiple directions by the user holding the sensor), wherein the second detection data is accurate data because the standard force sensor is a pre-calibrated sensor. After obtaining the first detection data and the second detection data, the first detection data can be input into the neural network model to determine the prediction result, and the prediction result can be compared with the second detection data to determine the difference, and then the neural network model can be adjusted. By continuously adjusting the neural network model using a large amount of the first detection data and the second detection data, a trained neural network model can be finally obtained, through which the detection force of the force sensor and the final output result can be calibrated, so that a relatively accurate detection result can be obtained. Some existing solutions are to calibrate the force sensor by applying several fixed forces to it. However, with this solution, less data is obtained, resulting in an inaccurate mapping relationship between the detected force and the final result. With this solution, a large amount of continuous external force can be obtained, thereby obtaining a large amount of training data to train the model, thereby making the model more convergent, thereby improving the detection accuracy of the force sensor. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0022] Figure 1 is a schematic structural diagram of a force sensor according to an embodiment of the present application;

[0023] Figure 2 It is a structural schematic diagram of a data acquisition device according to an embodiment of the present application;

[0024] Figure 3 It is a schematic diagram of the training process of a neural network model of an embodiment of the present application;

[0025] Figure 4 is a schematic diagram of the structure of a neural network model of an embodiment of the present application;

[0026] Figure 5 is a flow chart of a method for calibrating a force sensor according to an embodiment of the present application;

[0027] Figure 6 It is a structural schematic diagram of a calibration device for a force sensor according to an embodiment of the present application;

[0028] Figure 7 It is a structural block diagram of a network device according to an embodiment of the present application;

[0029] Figure 8 This is a structural block diagram of a user equipment according to an embodiment of the present application; DETAILED DESCRIPTION

[0030] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout identify the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0031] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "said", and "the" used herein may also include plural forms, and "multiple" refers to two or more, and other quantifiers are similar. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups. It should be understood that when we say that an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may be intermediate elements. In addition, the "connection" or "coupling" used here may include wireless connection or wireless coupling. The term "and / or" used here describes the association relationship of associated objects, indicating that there may be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0032] The solution of the present application can be applied in the calibration scenario of force sensors. The purpose of the force sensor calibration method is to determine the exact relationship between the sensor output and the applied force to ensure the reliability and accuracy of the measurement results. The specific implementation steps are to apply different contact forces to the force sensor, record the output signal of the corresponding force sensor, and establish a model of the relationship between the contact force and the output signal. For example, this solution can be applied in the calibration scenario of a three-dimensional force sensor. A neural network model can be trained, and the output signal of the three-dimensional force sensor can be calibrated through the neural network model to improve the accuracy of the detection results of the three-dimensional force sensor.

[0033] Specifically, the present solution can be provided with a target force sensor and a standard force sensor for detecting the same external force, the target force sensor can be a three-dimensional force sensor, and the standard force sensor is a pre-calibrated force sensor; the target force sensor and the standard force sensor can obtain the first detection data and the second detection data by applying a continuous external force (such as applying multiple different forces in multiple directions by the user holding the sensor), wherein the second detection data is accurate data because the standard force sensor is a pre-calibrated sensor. Some existing solutions calibrate the force sensor by applying several fixed forces to the force sensor, but with this solution, the data obtained is small, resulting in an inaccurate mapping relationship between the detected force and the final result, while with this solution, a large number of continuous external forces can be obtained, thereby obtaining a large number of training data to train the model, thereby making the model more convergent, thereby improving the detection accuracy of the force sensor. The first detection data and the second detection data are generated by a continuous external force within a period of time, and the present solution can align the first detection data and the second detection data (align in time) to form multiple sets of training data (corresponding to the same force at different times), and then train the model. The model may also be trained with nonlinear changes between continuous first detection data and continuous second detection data.

[0034] In an alternative solution, Figure 1 As shown, the three-dimensional force sensor is composed of an integrated elastic matrix 1 and an optical fiber 2, wherein the elastic matrix 1 includes a first region 1.1, a second region 1.2 and a third region 1.3; wherein the first region 1.1 and the second region 1.2 adopt a cantilever beam structure, which is placed crosswise at an angle of 90 degrees, and the third region 1.3 is a hollow tubular structure and is engraved with rectangular grooves to form a multi-layer continuous cantilever beam.

[0035] In an alternative solution, Figure 2 As shown, the present application can be designed to be used for data acquisition equipment for detection, and a large amount of data can be collected through the data acquisition equipment for model training. Specifically, the data acquisition equipment includes: a first clamp 2 for fixing the three-dimensional force sensor 1 and a second clamp 4 for installing the first clamp 2, and the standard force sensor 3 is arranged outside the first clamp 2. In one embodiment, the three-dimensional force sensor 1 can be a generally cylindrical structure, the first clamp 2 is sleeved outside the three-dimensional force sensor 1, and the standard force sensor 3 is sleeved outside the first clamp 2. The second clamp 4 is used to fix the three-dimensional force sensor 1, the first clamp 2 and the standard force sensor 3, and the three-dimensional force sensor 1 and the standard force sensor 3 can be fixed on the second clamp 4 through the first clamp 2, and the second clamp 4 can be fixed on the platform.

[0036] When applying an external force, the external force can be applied by hand-holding a clamp or other means, so that the three-dimensional force sensor and the standard force sensor detect the same external force. This solution can collect data on the external force over a period of time through the three-dimensional force sensor and the standard force sensor to form first detection data and second detection data. In addition, the three-dimensional force sensor has a corresponding coordinate system, which is composed of three mutually perpendicular first coordinate directions, and the standard force sensor also has a coordinate system, which is composed of three mutually perpendicular second coordinate directions. This solution can align the two coordinate systems by manual adjustment or automatic adjustment by the user, so that the first coordinate direction and the second coordinate direction point to the same. It is also possible to obtain the mapping relationship of the coordinate systems when the two coordinate systems are not aligned (the first coordinate direction and the second coordinate direction point to at least partially different), and perform data conversion and alignment between the two force sensors (three-dimensional force sensor and standard force sensor) according to the mapping relationship. When the coordinate systems are different, the first coordinate direction and the second coordinate direction can be the same or different, and can be configured according to needs.

[0037] After obtaining data through two force sensors, the obtained data can be used to train the model, such as Figure 3 As shown, the data from the three-dimensional force sensor can be used as input data, and the data obtained by the standard force sensor can be used as annotated data (or labels) to form multiple groups of data. The multiple groups of data can then be divided into training sets and validation sets. The training set is used to train the model, and the validation set is used to verify whether the model has converged. 80% of the data can be used as the training set, and 20% of the data can be used as the validation set. After that, a neural network model can be constructed. The neural network model of this solution can adopt a backpropagation (BP) neural network with an activation function (LeakyRectified Linear Unit, LekyReLU). The BP neural network uses a backpropagation algorithm to optimize the weights and biases of the neural network. As shown in FIG. Figure 4 As shown, the BP neural network can be composed of an input layer (input), a hidden layer (hidden layer) and an output layer (output), and the hidden layer can have at least one layer.

[0038] After the neural network model is constructed, the model training can be performed based on the first detection data and the second detection data of the training set. The first detection data can be input into the neural network model to determine the prediction result, and the prediction result can be compared with the second detection data to determine the difference, and then the neural network model can be adjusted. The neural network model can be continuously adjusted by using a large amount of first detection data and second detection data, and the model can be verified by using a verification set to verify whether the error of the model meets the requirements. Finally, a trained neural network model can be obtained, and it can be evaluated and applied. Through the neural network model, the detection force of the force sensor and the final output result can be calibrated, so that a more accurate detection result can be obtained.

[0039] Specifically, the present application provides a method for calibrating a force sensor. Figure 5 As shown, the method includes:

[0040] Step 502: Acquire first detection data of continuous external force based on the target force sensor.

[0041] Step 504, obtaining second detection data of continuous external force based on the standard force sensor, the force sensor and the standard force sensor are arranged on the data acquisition device and detect the same external force. Specifically, as an optional embodiment, the data acquisition device includes: a first clamp for fixing the three-dimensional force sensor and a second clamp for installing the first clamp, and the standard force sensor is arranged outside the first clamp. The three-dimensional force sensor and the standard force sensor are in contact with the first clamp together, so that when the first clamp is subjected to an external force, the three-dimensional force sensor and the standard force sensor can feel the same force. Specifically, as an optional embodiment, the three-dimensional force sensor is composed of an integrated elastic matrix and an optical fiber, and the elastic matrix includes a first area, a second area and a third area; wherein the first area and the second area adopt a cantilever beam structure, which is placed crosswise at a 90-degree angle, and the third area is a hollow tubular structure, and is engraved with rectangular grooves to form a multi-layer continuous cantilever beam.

[0042] Step 506: input the first detection data into the neural network model to determine the prediction result.

[0043] Step 508: adjust the neural network model according to the prediction result and the second detection data, determine the trained neural network model, and calibrate the target force sensor through the trained neural network model.

[0044] This solution can be used to set up a target force sensor and a standard force sensor for detecting the same external force. The target force sensor can be a three-dimensional force sensor, and the standard force sensor is a pre-calibrated force sensor. The target force sensor and the standard force sensor can obtain first detection data and second detection data by applying continuous external force (such as applying multiple different forces in multiple directions by the user holding the hand), wherein the second detection data is accurate data because the standard force sensor is a pre-calibrated sensor. After obtaining the first detection data and the second detection data, the first detection data can be input into the neural network model to determine the prediction result, and the prediction result can be compared with the second detection data to determine the difference, and then the neural network model can be adjusted. By using a large amount of first detection data and second detection data to continuously adjust the neural network model, a trained neural network model can be finally obtained. The detection force of the force sensor and the final output result can be calibrated through the neural network model, so that a relatively accurate detection result can be obtained. Some existing solutions are to calibrate the force sensor by applying several fixed forces to it. However, with this solution, less data is obtained, resulting in an inaccurate mapping relationship between the detected force and the final result. With this solution, a large amount of continuous external force can be obtained, thereby obtaining a large amount of training data to train the model, thereby making the model more convergent, thereby improving the detection accuracy of the force sensor.

[0045] The scheme of the present application can adopt a BP neural network model. Specifically, as an optional embodiment, the target force sensor is a three-dimensional force sensor, and the neural network model includes: an input layer, which is used to input the input detection data into a hidden layer, and the detection data is determined according to the force detection information in three mutually perpendicular first coordinate directions; a hidden layer, which is used to analyze the detection data and determine the prediction result; an output layer, which is used to output the prediction result, and the prediction result includes the force prediction results in the three mutually perpendicular second coordinate directions. Specifically, as an optional embodiment, the neural network model is adjusted according to the prediction result and the second detection data to determine the trained neural network model, including: comparing the prediction result with the second detection data to determine the difference; determining the parameter adjustment amount of the neural network model according to the difference; and reversely adjusting the neural network model according to the parameter adjustment amount. Among them, the detection data can be the first detection data, and the detection data can be the data converted by the mapping relationship between the coordinate systems or the data that has not been converted. It can be converted in the model or after the prediction result is generated.

[0046] The processing process of the BP neural network model in this scheme is mainly divided into two stages: forward propagation and back propagation. The forward propagation process consists of an input layer, a hidden layer, and an output layer. The input layer passes the input sample (the first detection data) to the hidden layer of the network, and the hidden layer passes the activated result to the output layer, which gives the final prediction result. The back propagation process calculates the error of the output layer based on the prediction result of the network and the actual label (the second detection data); then uses the chain rule to calculate the error of the hidden layer; uses the error to update the weight and bias of the network to minimize the loss function; and gradually optimizes the weight and bias parameters to achieve the mapping and prediction of the input data. The input value can be the center wavelength drift value of FBG1, FBG2, and FBG3, and the output value is the force component in the three mutually perpendicular coordinate directions of X, Y, and Z. The Adam optimizer was used, and the learning rate (0.0005), the number of hidden layers (3), the number of hidden nodes per layer (100), and the number of training rounds (1000) were set. Automatically learn the complex mapping relationship between the input and output of the force sensor, continuously optimize and update the model by learning a large number of input-output data samples, and obtain better data fitting effects, thereby realizing load calibration of the force sensor in a data-driven manner.

[0047] In actual operation, the coordinate systems of the two sensors can be aligned by manually adjusting the three-dimensional force sensor and the standard force sensor. Specifically, as an optional embodiment, the first coordinate direction and the second coordinate direction point to the same direction. The three first coordinate directions and the three second coordinate directions are the same. This solution can also be analyzed when the coordinate systems of the two sensors are not exactly the same, and the information detected by the sensors can be adjusted according to the mapping relationship to obtain the first detection data or the second detection data. Specifically, as an optional embodiment, the first coordinate direction and the second coordinate direction point to at least partially different directions, and the method further includes: obtaining a mapping relationship between the first coordinate direction and the second coordinate direction; adjusting the detection information of the three-dimensional force sensor or the detection information of the standard force sensor according to the mapping relationship.

[0048] When the coordinate systems of the two sensors are not completely the same, the prediction result or the second detection data can be adjusted and aligned according to the mapping relationship, so as to compare and determine the difference. Specifically, as an optional embodiment, the first coordinate direction and the second coordinate direction point to at least partially different directions, and the prediction result is compared with the second detection data, including: obtaining the mapping relationship between the first coordinate direction and the second coordinate direction; adjusting the prediction result or the second detection data according to the mapping relationship, and comparing the adjusted data to determine the difference.

[0049] This solution can not only be used for static calibration of force sensors, but also for testing calibrated force sensors. Specifically, as an optional embodiment, the method also includes: obtaining target detection data of the force sensor to be verified for the force to be detected; inputting the target detection data into the trained neural network model to determine the calibration data of the force to be detected; and verifying the force sensor to be verified according to the calibration data. The force sensor to be verified has target detection data (unprocessed collected data) and output results (output after processing of the collected data). After obtaining the calibration data, the calibration data can be compared with the output results of the force sensor to be verified to determine the difference, and then determine whether the force sensor to be verified is accurate.

[0050] Based on the above embodiments, the present application also provides a calibration device for a force sensor, such as Figure 6 As shown, the device comprises:

[0051] The first data acquisition module 602 is used to acquire first detection data of continuous external force based on the force sensor.

[0052] The second data acquisition module 604 is used to acquire continuous second detection data of the external force based on the standard force sensor.

[0053] The prediction result acquisition module 606 is used to input the first detection data into the neural network model to determine the prediction result.

[0054] The model training processing module 608 is used to adjust the neural network model according to the prediction result and the second detection data, determine the trained neural network model, and calibrate the target force sensor through the trained neural network model.

[0055] The implementation of the embodiment of the present application is similar to the implementation of the above-mentioned method embodiment. The specific implementation can refer to the specific implementation of the above-mentioned method embodiment, which will not be repeated here.

[0056] This solution can be used to set up a target force sensor and a standard force sensor for detecting the same external force. The target force sensor can be a three-dimensional force sensor, and the standard force sensor is a pre-calibrated force sensor. The target force sensor and the standard force sensor can obtain first detection data and second detection data by applying continuous external force (such as applying multiple different forces in multiple directions by the user holding the hand), wherein the second detection data is accurate data because the standard force sensor is a pre-calibrated sensor. After obtaining the first detection data and the second detection data, the first detection data can be input into the neural network model to determine the prediction result, and the prediction result can be compared with the second detection data to determine the difference, and then the neural network model can be adjusted. By using a large amount of first detection data and second detection data to continuously adjust the neural network model, a trained neural network model can be finally obtained. The detection force of the force sensor and the final output result can be calibrated through the neural network model, so that a relatively accurate detection result can be obtained. Some existing solutions are to calibrate the force sensor by applying several fixed forces to it. However, with this solution, less data is obtained, resulting in an inaccurate mapping relationship between the detected force and the final result. With this solution, a large amount of continuous external force can be obtained, thereby obtaining a large amount of training data to train the model, thereby making the model more convergent, thereby improving the detection accuracy of the force sensor.

[0057] It should be noted that the division of units and / or modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit and / or module in each embodiment of the present application may be integrated into a processing unit and / or module, or each unit and / or module may exist physically separately, or two or more units and / or modules may be integrated into one unit and / or module. The above-mentioned integrated units and / or modules may be implemented in the form of hardware or in the form of software functional units and / or modules.

[0058] If the integrated units and / or modules are implemented in the form of software functional units and / or modules and sold or used as independent products, they can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0059] In addition, the data transmission device and the data transmission method provided in the above embodiments are based on the same application concept. Since the principles of solving problems by the method and the device are similar, the implementation of the device and the method can refer to each other, and the repeated parts will not be repeated.

[0060] Figure 7 A structural block diagram of a network device is shown according to an exemplary embodiment.

[0061] like Figure 7 As shown, the network device 1100 includes at least: a processor 1110 , a memory 1120 , and a transceiver 1130 .

[0062] The transceiver 1130 is used to receive and send data under the control of the processor 1110 .

[0063] exist Figure 7 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 1110 and memory represented by memory 1120. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1130 may be a plurality of components, namely, a transmitter and a receiver, providing units and / or modules for communicating with various other devices on a transmission medium, which may include a wireless channel, a wired channel, an optical cable, and other transmission media.

[0064] The processor 1110 is responsible for managing the bus architecture and general processing, and the memory 1120 can store data used by the processor 1110 when performing operations.

[0065] Optionally, the processor 1110 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD), and the processor 1110 may also adopt a multi-core architecture. The processor 1110 and the memory 1120 may also be physically arranged separately.

[0066] The processor 1110 calls the computer program stored in the memory 1120 to execute any one of the methods for allocating a cell radio network temporary identifier provided in the above embodiments of the present application according to the obtained executable instructions.

[0067] Figure 8 A structural block diagram of a user equipment is shown according to an exemplary embodiment.

[0068] like Figure 8 As shown, the user equipment 1300 includes at least: a processor 1310 , a memory 1320 , and a transceiver 1330 .

[0069] The transceiver 1330 is used to receive and send data under the control of the processor 1310 .

[0070] exist Figure 8 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 1310 and various circuits of memory represented by memory 1320 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1330 may be a plurality of components, namely, a transmitter and a receiver, providing units and / or modules for communicating with various other devices on a transmission medium, including transmission media such as wireless channels, wired channels, and optical cables. For different user devices, the user interface 1340 may also be an interface capable of externally and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0071] The processor 1310 is responsible for managing the bus architecture and general processing, and the memory 1320 can store data used by the processor 1310 when performing operations.

[0072] Optionally, the processor 1310 may be a CPU (central processing unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or a CPLD (Complex Programmable Logic Device), and the processor 1310 may also adopt a multi-core architecture. The processor 1310 and the memory 1320 may also be physically arranged separately.

[0073] The processor 1310 calls the computer program stored in the memory 1320 to execute any one of the methods for allocating a cell radio network temporary identifier provided in the above embodiments of the present application according to the obtained executable instructions.

[0074] It should be noted here that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0075] In addition, a storage medium is provided in an embodiment of the present application, on which a computer program is stored, and when the computer program is executed by the processor, the data transmission method in the above embodiments is implemented. The storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic storage (such as floppy disk, hard disk, tape, magneto-optical disk (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid state drive (SSD)), etc.

[0076] In an embodiment of the present application, a program product is provided, for example, the program product is an FPGA chip or a DSP chip, and the program product includes executable instructions, and the executable instructions are stored in a storage medium. The processor reads the executable instructions from the storage medium, so that when the executable instructions are executed by the processor, the data transmission method in each of the above embodiments is implemented.

[0077] This solution can be used to set up a target force sensor and a standard force sensor for detecting the same external force. The target force sensor can be a three-dimensional force sensor, and the standard force sensor is a pre-calibrated force sensor. The target force sensor and the standard force sensor can obtain first detection data and second detection data by applying continuous external force (such as applying multiple different forces in multiple directions by the user holding the hand), wherein the second detection data is accurate data because the standard force sensor is a pre-calibrated sensor. After obtaining the first detection data and the second detection data, the first detection data can be input into the neural network model to determine the prediction result, and the prediction result can be compared with the second detection data to determine the difference, and then the neural network model can be adjusted. By using a large amount of first detection data and second detection data to continuously adjust the neural network model, a trained neural network model can be finally obtained. The detection force of the force sensor and the final output result can be calibrated through the neural network model, so that a relatively accurate detection result can be obtained. Some existing solutions are to calibrate the force sensor by applying several fixed forces to it. However, with this solution, less data is obtained, resulting in an inaccurate mapping relationship between the detected force and the final result. With this solution, a large amount of continuous external force can be obtained, thereby obtaining a large amount of training data to train the model, thereby making the model more convergent, thereby improving the detection accuracy of the force sensor.

[0078] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0079] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0083] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for calibrating a force sensor, characterized in that: The method comprises: Acquiring first detection data of continuous external force based on the target force sensor; Acquiring second detection data of continuous external force based on a standard force sensor, wherein the force sensor and the standard force sensor are arranged on a data acquisition device and detect the same external force; Inputting the first detection data into the neural network model to determine the prediction result; The neural network model is adjusted according to the prediction result and the second detection data to determine a trained neural network model so as to calibrate the target force sensor through the trained neural network model.

2. The method according to claim 1, characterized in that The target force sensor is a three-dimensional force sensor, and the neural network model includes: An input layer, used to input input detection data into the hidden layer, wherein the detection data is determined based on force detection information in three mutually perpendicular first coordinate directions; Hidden layer, used to analyze the test data and determine the prediction results; The output layer is used to output prediction results, wherein the prediction results include force prediction results in the three mutually perpendicular second coordinate directions.

3. The method according to claim 2, characterized in that The neural network model is adjusted according to the prediction result and the second detection data to determine the trained neural network model, including: Comparing the prediction result with the second test data to determine the difference; Determine the parameter adjustment amount of the neural network model according to the difference amount; Reversely adjust the neural network model according to the parameter adjustment amount.

4. The method according to claim 2, characterized in that: The first coordinate direction and the second coordinate direction point to the same direction.

5. The method according to claim 2, characterized in that: The first coordinate direction and the second coordinate direction point to at least partially different directions, and the method further includes: Obtaining a mapping relationship between a first coordinate direction and a second coordinate direction; The detection information of the three-dimensional force sensor or the detection information of the standard force sensor is adjusted according to the mapping relationship.

6. The method according to claim 3, characterized in that The first coordinate direction and the second coordinate direction are at least partially different, and comparing the prediction result with the second detection data includes: Obtaining a mapping relationship between a first coordinate direction and a second coordinate direction; The prediction result or the second detection data is adjusted according to the mapping relationship, and the adjusted data is compared to determine the difference.

7. The method according to claim 2, characterized in that: The data acquisition device comprises: a first fixture for fixing the three-dimensional force sensor and a second fixture for installing the first fixture, and the standard force sensor is arranged outside the first fixture.

8. The method according to claim 7, characterized in that The three-dimensional force sensor is composed of an integrated elastic matrix and optical fiber, and the elastic matrix includes a first area, a second area and a third area; wherein the first area and the second area adopt a cantilever beam structure, which are placed crosswise at a 90-degree angle, and the third area is a hollow tubular structure and is engraved with rectangular grooves to form a multi-layer continuous cantilever beam.

9. The method according to claim 1, characterized in that: The method further comprises: Obtaining target detection data of the force sensor to be calibrated for the force to be detected; Input the target detection data into the trained neural network model to determine the calibration data of the force to be detected; Calibrate the force sensor to be calibrated according to the calibration data.

10. A calibration device for a force sensor, characterized in that: The device comprises: A first data acquisition module, used for acquiring first detection data of continuous external force based on the force sensor; A second data acquisition module, used for acquiring second detection data of continuous external force based on the standard force sensor; A prediction result acquisition module, used for inputting the first detection data into the neural network model to determine the prediction result; The model training processing module is used to adjust the neural network model according to the prediction result and the second detection data, determine the trained neural network model, and calibrate the target force sensor through the trained neural network model.

Images