Environmental factor compensation method, device and equipment for gallium nitride Hall current sensor
By establishing an environmental error compensation model, the measurement errors caused by factors such as temperature, humidity, and electromagnetic interference of the gallium nitride Hall current sensor are compensated in real time. This solves the problem that the hardware compensation mechanism cannot adapt to complex environments, improves measurement accuracy and stability, and expands the application scope.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-27
- Publication Date
- 2026-04-07
AI Technical Summary
Existing hardware compensation mechanisms are insufficient to effectively address the nonlinear coupling effects of gallium nitride Hall current sensors under complex environmental conditions, resulting in insufficient measurement accuracy and stability, and failing to meet the application requirements of high-performance sensors.
By establishing an environmental error compensation model, machine learning or regression analysis is used to train the mapping relationship between the current measurement error of the gallium nitride Hall current sensor and various environmental conditions, and the measurement error caused by factors such as temperature, humidity and electromagnetic interference is compensated in real time.
It achieves accurate quantification and real-time compensation of complex environmental factors, significantly improving the measurement accuracy and stability of the sensor under harsh working conditions, and broadening its application prospects in high-end fields such as new energy vehicles and industrial control.
Smart Images
Figure CN121805926A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of sensors, in particular to a method, device and equipment for compensating environmental factors of a gallium nitride Hall current sensor. BACKGROUND
[0002] In practical applications, the measurement accuracy of a Hall current sensor is easily affected by environmental temperature, resulting in temperature drift. To overcome this problem, compensation schemes based on hardware circuits are commonly used in the prior art. A typical conventional compensation method is to use the temperature characteristics of semiconductor devices for reverse compensation, for example, by using the temperature drift characteristics of a diode or a zener tube to jointly compensate the temperature of a Hall element. Specifically, this type of scheme usually integrates a compensation element (such as a diode) with a specific temperature coefficient in the signal conditioning circuit of the sensor, and uses the change of its parameters with temperature to partially offset the change of the sensitivity or output offset of the Hall element with temperature.
[0003] However, this hardware compensation method has obvious limitations. First, its compensation effect is heavily dependent on the matching accuracy of the temperature characteristics between the compensation element and the Hall element, and individual differences and batch dispersion exist in the components themselves, resulting in poor compensation consistency and difficulty in accurate calibration. Second, this type of method can only roughly and linearly compensate for a single factor, and cannot effectively cope with other environmental factors such as humidity, electromagnetic interference and the complex nonlinear coupling effects formed by temperature. In addition, the hardware compensation scheme lacks flexibility, and once the circuit design is fixed, the compensation characteristics are difficult to adjust and optimize, and cannot adapt to the performance degradation of the sensor during use or the differentiated needs of different application scenarios. With the increasing demand for measurement accuracy, especially in a wide temperature range and complex electromagnetic environment, this single and fixed hardware compensation mechanism has been difficult to meet the application needs of high-performance Hall current sensors such as gallium nitride. SUMMARY
[0004] The embodiments of the present application provide a method, device and equipment for compensating environmental factors of a gallium nitride Hall current sensor to solve the problem that the current hardware compensation mechanism cannot meet the application needs of a gallium nitride Hall current sensor.
[0005] In a first aspect, the embodiments of the present application provide a method for compensating environmental factors of a gallium nitride Hall current sensor, comprising: obtaining a measured output voltage of the gallium nitride Hall current sensor under current environmental conditions; wherein the environmental conditions include temperature, humidity and electromagnetic interference intensity; input the measured output voltage and the current environmental condition into the trained environmental error compensation model to obtain a current measurement compensation quantity corresponding to the measured output voltage and the current environmental condition; wherein the environmental error compensation model is used to represent a mapping relationship between the current measurement error of the gallium nitride Hall current sensor and the multiple environmental conditions; compensate the output current corresponding to the measured output voltage based on the current measurement compensation quantity to obtain an accurate current measurement value.
[0006] In a possible implementation, before inputting the measured output voltage and the current environmental condition into the trained environmental error compensation model to obtain a current measurement compensation quantity corresponding to the measured output voltage and the current environmental condition, the method further includes: obtain, through experiments, the current measurement error of the gallium nitride Hall current sensor under multiple environmental conditions to obtain multiple sets of environmental condition-current measurement error data; train the initial environmental error compensation model based on the multiple sets of environmental condition-current measurement error data to obtain the trained environmental error compensation model.
[0007] In a possible implementation, the environmental error compensation model includes an intrinsic compensation model and a device compensation model, and each set of environmental condition-current measurement error data further includes a device measurement error; training the initial environmental error compensation model based on the multiple sets of environmental condition-current measurement error data to obtain the trained environmental error compensation model includes: for each set of environmental condition-current measurement error data, separating the device measurement error corresponding to the environmental condition from the current measurement error data to obtain multiple sets of environmental condition-intrinsic measurement error data; training the initial environmental error compensation model based on the multiple sets of environmental condition-intrinsic measurement error data to obtain the trained environmental error compensation model.
[0008] In a possible implementation, before separating the device measurement error corresponding to the environmental condition from the current measurement error data to obtain multiple sets of environmental condition-intrinsic measurement error data for each set of environmental condition-current measurement error data, the method further includes: obtaining, through experiments, the device measurement error corresponding to the multiple environmental conditions.
[0009] In a possible implementation, obtaining, through experiments, the current measurement error of the gallium nitride Hall current sensor under multiple environmental conditions to obtain multiple sets of environmental condition-current measurement error data includes: under an electromagnetic interference shielding environment, changing the temperature and the humidity, and measuring to obtain multiple sets of first environmental condition-current measurement error data; In a constant temperature and humidity environment, the electromagnetic interference intensity is changed, and a plurality of groups of first environmental condition-current measurement error data are measured; Correspondingly, the environmental error compensation model includes a temperature-humidity joint influence sub-model and an electromagnetic effect influence sub-model; based on the plurality of groups of environmental condition-current measurement error data, the initial environmental error compensation model is trained to obtain a trained environmental error compensation model, including: Based on the plurality of groups of first environmental condition-current measurement error data, the initial temperature-humidity joint influence sub-model is trained to obtain a trained temperature-humidity joint influence sub-model; Based on the plurality of groups of second environmental condition-current measurement error data, the initial electromagnetic effect influence sub-model is trained to obtain a trained electromagnetic effect influence sub-model.
[0010] In a possible implementation, the measured output voltage and the current environmental condition are input into the trained environmental error compensation model to obtain a current measurement compensation quantity corresponding to the measured output voltage and the current environmental condition, including: The measured output voltage, the current temperature, and the current humidity are input into the trained temperature-humidity joint influence sub-model to obtain a first current measurement compensation quantity; The measured output voltage and the current electromagnetic interference intensity are input into the trained electromagnetic effect influence sub-model to obtain a second current measurement compensation quantity; The first current measurement compensation quantity and the second current measurement compensation quantity are input into a preset temperature-humidity-electromagnetic effect coupling formula to obtain an intrinsic current measurement compensation quantity corresponding to the current environmental condition; The sum of the intrinsic current measurement compensation quantity and a device measurement error corresponding to the current environmental condition is calculated to obtain a current measurement compensation quantity corresponding to the current environmental condition.
[0011] In a possible implementation, before the first current measurement compensation quantity and the second current measurement compensation quantity are input into the preset temperature-humidity-electromagnetic effect coupling formula to obtain the intrinsic current measurement compensation quantity corresponding to the current environmental condition, the method further includes: Based on the plurality of groups of first environmental condition-current measurement error data and the plurality of groups of first environmental condition-current measurement error data, polynomial fitting is performed to obtain the temperature-humidity-electromagnetic effect coupling formula.
[0012] In a second aspect, the embodiments of the present application provide an environmental factor compensation device of a gallium nitride Hall current sensor, including: The acquisition module is configured to acquire a measured output voltage of the gallium nitride Hall current sensor under a current environmental condition; wherein the environmental condition includes temperature, humidity, and electromagnetic interference intensity; The mapping module is used to input the measured output voltage and current environmental conditions into the trained environmental error compensation model to obtain the current measurement compensation amount corresponding to the measured output voltage and current environmental conditions; wherein, the environmental error compensation model is used to characterize the mapping relationship between the current measurement error of the gallium nitride Hall current sensor and various environmental conditions; The compensation module is used to compensate the output current corresponding to the measured output voltage based on the current measurement compensation amount, so as to obtain an accurate current measurement value.
[0013] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect or any possible implementation thereof.
[0014] The environmental factor compensation method, apparatus, and device for gallium nitride Hall current sensors provided in this invention establish an environmental error compensation model. This model collaboratively analyzes the measured output voltage of the gallium nitride Hall current sensor with multi-dimensional environmental parameters such as temperature, humidity, and electromagnetic interference intensity. This achieves precise quantification and real-time compensation of measurement errors caused by environmental factors, effectively overcoming the shortcomings of existing technologies that fail to adequately consider complex environmental factors. It significantly improves the measurement accuracy and stability of the sensor under harsh operating conditions. Due to the data-driven modeling approach, this scheme can adaptively learn and compensate for nonlinear errors caused by the coupling effects of multiple environmental factors, avoiding the limitations of traditional single-parameter compensation. Without significantly increasing hardware costs, it enables gallium nitride Hall current sensors to maintain superior measurement performance across the entire temperature range, complex electromagnetic environments, and humidity conditions, greatly expanding its application prospects in high-end fields such as new energy vehicles and industrial control. Attached Figure Description
[0015] Figure 1 This is a flowchart illustrating the implementation of an environmental factor compensation method for a gallium nitride Hall current sensor according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the environmental factor compensation device for a gallium nitride Hall current sensor provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0016] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0017] See Figure 1 The flowchart illustrating the implementation of the environmental factor compensation method for the gallium nitride Hall current sensor provided in this embodiment of the invention is described in detail below: Step 101, obtaining a measured output voltage of the gallium nitride Hall current sensor under current environmental conditions; wherein the environmental conditions include temperature, humidity, and electromagnetic interference intensity; In this embodiment, the measured output voltage is the voltage signal finally output by the gallium nitride Hall current sensor after sensing the measured current and being processed by the internal signal conditioning circuit. The voltage value is proportional to the measured current, but contains errors introduced by environmental factors, which need to be corrected to obtain the actual current value.
[0018] The measured output voltage of the gallium nitride Hall current sensor under current environmental conditions is the starting point of the compensation process. The direct output of the Hall sensor is a voltage signal, and the influence of environmental factors is ultimately reflected in the deviation of this output voltage. At the same time, the compensation needs to know the current environmental state.
[0019] Specifically, the measured output voltage is obtained by directly sampling the output pin of the signal conditioning circuit of the Hall sensor through the ADC module of the microcontroller, the environmental temperature and humidity are read in real time by the digital temperature and humidity sensor installed on the sensor PCB, and the electromagnetic interference intensity is placed close to the sensor by a wideband field intensity probe or a dedicated EMI detection chip, and the output signal is connected to the ADC of the microcontroller for sampling and conversion.
[0020] Step 102, inputting the measured output voltage and the current environmental conditions into a trained environmental error compensation model to obtain a current measurement compensation amount corresponding to the measured output voltage and the current environmental conditions; wherein the environmental error compensation model is used to represent the mapping relationship between the current measurement error of the gallium nitride Hall current sensor and multiple environmental conditions.
[0021] In this embodiment, the current measurement compensation amount is the current value that needs to be added or subtracted from the initial current measurement value to correct the measurement error caused by environmental factors, and is a signed quantity. The environmental error compensation model is a mathematical model trained by machine learning or regression analysis, which establishes the mapping relationship between the sensor current measurement error and the environmental conditions and the working point (reflected by the measured output voltage).
[0022] The environmental error compensation model is essentially a function trained by a large amount of experimental data, which can capture the complex nonlinear relationship between multiple environmental factors and errors, so as to accurately predict how large the current measurement error is according to the current working state (output voltage) and environmental conditions.
[0023] Step 103, compensating the output current corresponding to the measured output voltage based on the current measurement compensation amount to obtain an accurate current measurement value.
[0024] In the embodiment, the measured output voltage is first converted into an initial current measurement value according to the nominal sensitivity of the sensor, and the measurement error estimation value calculated in the previous step is deducted from the initial current measurement value, so as to obtain an approximation value of the true current.
[0025] The embodiment of the application realizes accurate quantification and real-time compensation of measurement errors caused by environmental factors by establishing an environmental error compensation model, and cooperatively analyzes the measured output voltage of the gallium nitride Hall current sensor and multi-dimensional environmental parameters such as temperature, humidity and electromagnetic interference intensity, can effectively overcome the defects of insufficient consideration of complex environmental factors in the prior art, and significantly improves the measurement accuracy and stability of the sensor under harsh working conditions. Since a data-driven modeling method is used, the scheme can adaptively learn and compensate the nonlinear errors caused by the coupling of multiple environmental factors, avoiding the limitations of the traditional single parameter compensation effect, and can maintain the superior measurement performance of the gallium nitride Hall current sensor under the whole temperature range, complex electromagnetic environment and humidity conditions without significantly increasing the hardware cost, greatly widening the application prospect of the sensor in new energy vehicles, industrial control and other high-end fields.
[0026] In a possible implementation, before the measured output voltage and the current environmental condition are input into the trained environmental error compensation model to obtain the current measurement compensation quantity corresponding to the measured output voltage and the current environmental condition, the method further includes: Obtain the current measurement error of the gallium nitride Hall current sensor under multiple environmental conditions through experiments, and obtain multiple sets of environmental condition-current measurement error data; Train the initial environmental error compensation model based on the multiple sets of environmental condition-current measurement error data, and obtain the trained environmental error compensation model.
[0027] In the embodiment, the gallium nitride Hall current sensor is placed in a high-low temperature test box, a humidity control box and an electromagnetic interference simulator, a series of accurate known currents (provided by a high-precision standard current source) are applied to the sensor under different combinations of environmental conditions (temperature, humidity and EMI), and the output voltage of the sensor is recorded. Based on the formula: measurement error = (sensor measurement value - standard current value), the current measurement error of each test point is calculated.
[0028] Then, the collected massive (environmental condition, measured output voltage, current measurement error) data are used as a data set, and a machine learning algorithm (such as linear regression, support vector machine, neural network) or polynomial fitting is used to train the initial model until the model prediction error converges to an acceptable range.
[0029] In the training, a plurality of types of initial models can be set to be trained respectively, and a final environmental error compensation model is selected from the models according to the errors after the training.
[0030] In a possible implementation, the environmental error compensation model comprises an intrinsic compensation model and a device compensation model, and each set of environmental condition-current measurement error data further comprises a device measurement error; the initial environmental error compensation model is trained based on the plurality of sets of environmental condition-current measurement error data to obtain a trained environmental error compensation model, comprising: For each set of environmental condition-current measurement error data, the device measurement error corresponding to the environmental condition is separated from the current measurement error data to obtain a plurality of sets of environmental condition-intrinsic measurement error data; The initial environmental error compensation model is trained based on the plurality of sets of environmental condition-intrinsic measurement error data to obtain a trained environmental error compensation model.
[0031] In this embodiment, the intrinsic measurement error refers to a measurement error generated by the gallium nitride Hall element itself affected by environmental factors, and the device measurement error refers to an error introduced by other devices (such as an operational amplifier, a reference voltage source of an ADC, etc.) in the sensor signal chain affected by environmental factors (mainly temperature). Such a setting is because the total error of the sensor is the superposition of the errors of the Hall element and the signal chain circuit. By separation, a more pure and stable error model can be established for the Hall element, avoiding the influence of batch differences or aging of the circuit elements on the universality of the model.
[0032] To realize the separation of the device measurement error, the device measurement error is additionally measured and recorded in the experiment. For example, the offset error is quantified by measuring the output voltage of the system at zero input current (i.e., zero-point drift V_offset), and the gain error is quantified by measuring the change in ADC reading of a precise reference voltage on the board. Among them, the offset error is the voltage value output by the signal chain (such as an amplifier, an ADC) when the input current is zero. It causes the entire transfer characteristic curve to be shifted up and down, introducing a fixed error at all current points. The gain error is the actual amplification / gain of the signal chain deviating from the ideal value. It causes the slope of the transfer characteristic curve to change, resulting in an error that increases linearly with the increase of the measured current. Total device measurement error = offset error + (ideal current measurement value x gain error) For each set of data, the intrinsic measurement error is calculated by the formula intrinsic measurement error = total current measurement error - device measurement error. The subsequent data of (environmental condition, intrinsic measurement error) are used to train the environmental error compensation model, and at this time, the model more accurately represents the characteristics of the Hall element itself.
[0033] In one possible implementation, before separating the device measurement error corresponding to the environmental condition from the current measurement error data for each set of environmental condition-current measurement error data to obtain multiple sets of environmental condition-intrinsic measurement error data, the method further includes: The measurement errors of the device under various environmental conditions were obtained through experiments.
[0034] In this embodiment, the specific method for obtaining the device measurement error can be to conduct a temperature and humidity test on the signal conditioning circuit board without Hall elements, and directly measure the drift of its output voltage, thereby establishing a lookup table or simple model of device measurement error with temperature and humidity.
[0035] Alternatively, in the testing of a complete sensor, by analyzing the output at the zero-current input point and the full-scale input point at different temperatures, the temperature drift coefficients of the amplifier bias and gain can be calculated, thereby calculating the device measurement error under any operating condition.
[0036] In one possible implementation, the current measurement error of the gallium nitride Hall current sensor under various environmental conditions is obtained through experimentation, resulting in multiple sets of environmental condition-current measurement error data, including: In an electromagnetic interference shielded environment, by changing the temperature and humidity, multiple sets of first environmental condition-current measurement error data were obtained. In a constant temperature and humidity environment, by changing the intensity of electromagnetic interference, multiple sets of first environmental condition-current measurement error data were obtained. Accordingly, the environmental error compensation model includes a temperature-humidity joint influence sub-model and an electromagnetic effect influence sub-model; based on multiple sets of environmental condition-current measurement error data, the initial environmental error compensation model is trained to obtain a trained environmental error compensation model, including: Based on multiple sets of first environmental condition-current measurement error data, the initial temperature-humidity joint influence sub-model is trained to obtain the trained temperature-humidity joint influence sub-model. Based on multiple sets of second environmental condition-current measurement error data, the initial electromagnetic effect influence sub-model is trained to obtain the trained electromagnetic effect influence sub-model.
[0037] In this embodiment, for the first environmental condition - current measurement error data, the EMI intensity is set to 0 in an anechoic chamber or shielded box, and the parameters of the high and low temperature test chamber and humidity control chamber are systematically changed for testing.
[0038] To address the second environmental condition—current measurement error data—a constant temperature and humidity point was set within the high and low temperature test chamber. Then, the output field strength of the electromagnetic interference simulator was systematically changed for testing.
[0039] Then, the first set of data was used to train a temperature-humidity joint influence sub-model with (temperature, humidity, measured output voltage) as input and (current measurement error) as output. The second set of data was used to train an electromagnetic effect influence sub-model with (EMI intensity, measured output voltage) as input and (current measurement error) as output.
[0040] Based on the above embodiments, before training, the device measurement error under the corresponding environmental conditions can be subtracted from the total error measured under the first / second environmental conditions to obtain the pure intrinsic measurement error, which can be used to train the pure temperature-humidity sub-model and electromagnetic effect sub-model.
[0041] This embodiment decomposes the complex problem and studies the effects of temperature and humidity under EMI shielding, which eliminates EMI interference and makes the temperature-humidity joint effect sub-model more accurate. Similarly, the same applies to studying the effects of EMI under constant temperature and humidity conditions.
[0042] In addition, during training, the prediction error under the combined effect of the two sub-models is used as the error of the environmental error compensation model, and the types of the two sub-models are selected based on this.
[0043] In one possible implementation, the measured output voltage and current environmental conditions are input into a trained environmental error compensation model to obtain the current measurement compensation amount corresponding to the measured output voltage and current environmental conditions, including: Input the measured output voltage, current temperature and current humidity into the trained temperature-humidity joint influence sub-model to obtain the first current measurement compensation amount; The measured output voltage and the current electromagnetic interference intensity are input into the trained electromagnetic effect influence sub-model to obtain the second current measurement compensation amount. Input the first current measurement compensation amount and the second current measurement compensation amount into the preset temperature-humidity-electromagnetic effect coupling formula to obtain the intrinsic current measurement compensation amount corresponding to the current environmental conditions. The sum of the intrinsic current measurement compensation and the device measurement error corresponding to the current environmental conditions is calculated to obtain the current measurement compensation corresponding to the current environmental conditions.
[0044] In this embodiment, the current measured output voltage, temperature, and humidity are input into the temperature-humidity joint influence sub-model, and the first current measurement compensation amount is output; the current measured output voltage and EMI intensity are input into the electromagnetic effect influence sub-model, and the second current measurement compensation amount is output.
[0045] Then, the two compensation values are substituted into the coupling formula, which might be: Intrinsic current measurement compensation = a*(first value) + b*(second value) + c*(first value)*(second value), where a, b, and c are coupling coefficients. This step aims to approximate the possible interaction between temperature and humidity effects and EMI effects.
[0046] By querying or calculating the device measurement error at the current temperature, we can ultimately obtain the total current measurement compensation amount = intrinsic current measurement compensation amount + device measurement error.
[0047] In one possible implementation, before inputting the first current measurement compensation amount and the second current measurement compensation amount into a preset temperature-humidity-electromagnetic effect coupling formula to obtain the intrinsic current measurement compensation amount corresponding to the current environmental conditions, the following is also included: Based on multiple sets of first environmental condition-current measurement error data, polynomial fitting was performed to obtain the temperature-humidity-electromagnetic effect coupling formula.
[0048] In this embodiment, the first set of data and the second set of data obtained in the previous embodiment are combined to obtain a complete dataset containing the combination of all environmental factors and the total measurement error. Then, the first current measurement compensation amount and the second current measurement compensation amount (as independent variables, calculated by each sub-model based on the original data) are used as inputs, and the corresponding intrinsic measurement error of the actual measurement is used as output. The least squares method or other methods are used to perform multiple linear or nonlinear regression to fit the coefficients in the coupling formula (such as a, b, c above) so that the output of the formula is closest to the true measurement value.
[0049] When fitting the model, a first-order (linearly additive) model can be tried first, and the residuals between the model's predicted values and the actual measured values can be analyzed. If the residuals show a significant non-linear distribution, it indicates that the model complexity is insufficient. In this case, second-order interaction terms or squared terms can be gradually added to observe whether the model accuracy is significantly improved. Finally, through cross-validation, the model order that performs best on the unknown test set can be selected.
[0050] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0051] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.
[0052] Figure 2A schematic diagram of the environmental factor compensation device for a gallium nitride Hall current sensor provided in an embodiment of the present invention is shown. For ease of explanation, only the parts relevant to the embodiment of the present invention are shown, and are described in detail below: like Figure 2 As shown, the environmental factor compensation device 2 for the gallium nitride Hall current sensor includes: The acquisition module 21 is used to acquire the measured output voltage of the gallium nitride Hall current sensor under the current environmental conditions; wherein, the environmental conditions include temperature, humidity and electromagnetic interference intensity; The mapping module 22 is used to input the measured output voltage and the current environmental conditions into the trained environmental error compensation model to obtain the current measurement compensation amount corresponding to the measured output voltage and the current environmental conditions; wherein, the environmental error compensation model is used to characterize the mapping relationship between the current measurement error of the gallium nitride Hall current sensor and various environmental conditions; The compensation module 23 is used to compensate the output current corresponding to the measured output voltage based on the current measurement compensation amount, so as to obtain an accurate current measurement value.
[0053] In one possible implementation, the mapping module 22 is also used for: Before inputting the measured output voltage and current environmental conditions into the trained environmental error compensation model to obtain the current measurement compensation amount corresponding to the measured output voltage and current environmental conditions, the current measurement error of the gallium nitride Hall current sensor under various environmental conditions is obtained through experiments, and multiple sets of environmental condition-current measurement error data are obtained. Based on multiple sets of environmental condition-current measurement error data, the initial environmental error compensation model is trained to obtain the trained environmental error compensation model.
[0054] In one possible implementation, the environmental error compensation model includes an intrinsic compensation model and a device compensation model, and each set of environmental condition-current measurement error data also includes device measurement errors; the mapping module 22 is specifically used for: For each set of environmental condition-current measurement error data, the device measurement error corresponding to that environmental condition is separated from the current measurement error data to obtain multiple sets of environmental condition-intrinsic measurement error data; The initial environmental error compensation model is trained based on multiple sets of environmental condition-intrinsic measurement error data to obtain the trained environmental error compensation model.
[0055] In one possible implementation, the mapping module 22 is also used for: Before separating the device measurement error corresponding to the environmental condition from the current measurement error data for each set of environmental condition-current measurement error data to obtain multiple sets of environmental condition-intrinsic measurement error data, the device measurement error corresponding to various environmental conditions is obtained through experiments.
[0056] In one possible implementation, the mapping module 22 is specifically used for: In an electromagnetic interference shielded environment, by changing the temperature and humidity, multiple sets of first environmental condition-current measurement error data were obtained. In a constant temperature and humidity environment, by changing the intensity of electromagnetic interference, multiple sets of first environmental condition-current measurement error data were obtained. Accordingly, the environmental error compensation model includes a temperature-humidity joint influence sub-model and an electromagnetic effect influence sub-model; based on multiple sets of environmental condition-current measurement error data, the initial environmental error compensation model is trained to obtain a trained environmental error compensation model, including: Based on multiple sets of first environmental condition-current measurement error data, the initial temperature-humidity joint influence sub-model is trained to obtain the trained temperature-humidity joint influence sub-model. Based on multiple sets of second environmental condition-current measurement error data, the initial electromagnetic effect influence sub-model is trained to obtain the trained electromagnetic effect influence sub-model.
[0057] In one possible implementation, the mapping module 22 is specifically used for: Input the measured output voltage, current temperature and current humidity into the trained temperature-humidity joint influence sub-model to obtain the first current measurement compensation amount; The measured output voltage and the current electromagnetic interference intensity are input into the trained electromagnetic effect influence sub-model to obtain the second current measurement compensation amount. Input the first current measurement compensation amount and the second current measurement compensation amount into the preset temperature-humidity-electromagnetic effect coupling formula to obtain the intrinsic current measurement compensation amount corresponding to the current environmental conditions. The sum of the intrinsic current measurement compensation and the device measurement error corresponding to the current environmental conditions is calculated to obtain the current measurement compensation corresponding to the current environmental conditions.
[0058] In one possible implementation, the mapping module 22 is also used for: Before inputting the first current measurement compensation amount and the second current measurement compensation amount into the preset temperature-humidity-electromagnetic effect coupling formula to obtain the intrinsic current measurement compensation amount corresponding to the current environmental conditions, polynomial fitting is performed based on multiple sets of first environmental condition-current measurement error data and multiple sets of first environmental condition-current measurement error data to obtain the temperature-humidity-electromagnetic effect coupling formula.
[0059] This invention establishes an environmental error compensation model, collaboratively analyzing the measured output voltage of the gallium nitride Hall current sensor with multi-dimensional environmental parameters such as temperature, humidity, and electromagnetic interference intensity. This achieves precise quantification and real-time compensation for measurement errors caused by environmental factors, effectively overcoming the shortcomings of existing technologies that fail to adequately consider complex environmental factors. It significantly improves the sensor's measurement accuracy and stability under harsh operating conditions. Due to the data-driven modeling approach, this scheme can adaptively learn and compensate for nonlinear errors caused by the coupling effects of multiple environmental factors, avoiding the limitations of traditional single-parameter compensation. Without significantly increasing hardware costs, it enables the gallium nitride Hall current sensor to maintain superior measurement performance across the entire temperature range, complex electromagnetic environments, and humidity conditions, greatly expanding its application prospects in high-end fields such as new energy vehicles and industrial control.
[0060] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 3 As shown, the electronic device 3 of this embodiment includes a processor 30 and a memory 31. The memory 31 stores a computer program 32. When the processor 30 executes the computer program 32, it implements the steps in the various method embodiments described above. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the various device embodiments described above.
[0061] For example, computer program 32 may be divided into one or more modules / units, which are stored in memory 31 and executed by processor 30 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 32 in electronic device 3.
[0062] Electronic device 3 may include, but is not limited to, processor 30 and memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of electronic device 3 and does not constitute a limitation on electronic device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 3 may also include input / output devices, network access devices, buses, etc.
[0063] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.
[0064] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.
[0065] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.
Claims
1. A method for compensating for environmental factors in a gallium nitride Hall current sensor, characterized in that, include: Obtain the measured output voltage of the gallium nitride Hall current sensor under current environmental conditions; wherein, the environmental conditions include temperature, humidity and electromagnetic interference intensity; The measured output voltage and current environmental conditions are input into a trained environmental error compensation model to obtain the current measurement compensation amount corresponding to the measured output voltage and current environmental conditions; wherein, the environmental error compensation model is used to characterize the mapping relationship between the current measurement error of the gallium nitride Hall current sensor and various environmental conditions; The output current corresponding to the measured output voltage is compensated based on the current measurement compensation amount to obtain an accurate current measurement value.
2. The environmental factor compensation method for the gallium nitride Hall current sensor according to claim 1, characterized in that, Before inputting the measured output voltage and current environmental conditions into the trained environmental error compensation model to obtain the current measurement compensation amount corresponding to the measured output voltage and current environmental conditions, the method further includes: The current measurement error of the gallium nitride Hall current sensor under various environmental conditions was obtained through experiments, and multiple sets of environmental condition-current measurement error data were obtained. Based on the multiple sets of environmental condition-current measurement error data, the initial environmental error compensation model is trained to obtain the trained environmental error compensation model.
3. The environmental factor compensation method for the gallium nitride Hall current sensor according to claim 2, characterized in that, The environmental error compensation model includes an intrinsic compensation model and a device compensation model. Each set of environmental condition-current measurement error data also includes device measurement errors. The process of training the initial environmental error compensation model based on the multiple sets of environmental condition-current measurement error data to obtain a trained environmental error compensation model includes: For each set of environmental condition-current measurement error data, the device measurement error corresponding to that environmental condition is separated from the current measurement error data to obtain multiple sets of environmental condition-intrinsic measurement error data; The initial environmental error compensation model is trained based on the multiple sets of environmental condition-intrinsic measurement error data to obtain the trained environmental error compensation model.
4. The environmental factor compensation method for the gallium nitride Hall current sensor according to claim 3, characterized in that, Before separating the device measurement error corresponding to the environmental condition from the current measurement error data for each set of environmental condition-current measurement error data to obtain multiple sets of environmental condition-intrinsic measurement error data, the method further includes: The measurement errors of the device under various environmental conditions were obtained through experiments.
5. The environmental factor compensation method for the gallium nitride Hall current sensor according to claim 2, characterized in that, The experiment was conducted to obtain the current measurement error of the gallium nitride Hall current sensor under various environmental conditions, resulting in multiple sets of environmental condition-current measurement error data, including: In an electromagnetic interference shielded environment, by changing the temperature and humidity, multiple sets of first environmental condition-current measurement error data were obtained. In a constant temperature and humidity environment, by changing the intensity of electromagnetic interference, multiple sets of first environmental condition-current measurement error data were obtained. Accordingly, the environmental error compensation model includes a temperature-humidity joint influence sub-model and an electromagnetic effect influence sub-model; the step of training the initial environmental error compensation model based on the multiple sets of environmental condition-current measurement error data to obtain a trained environmental error compensation model includes: Based on the multiple sets of first environmental condition-current measurement error data, the initial temperature-humidity joint influence sub-model is trained to obtain the trained temperature-humidity joint influence sub-model. Based on the multiple sets of second environmental condition-current measurement error data, the initial electromagnetic effect influence sub-model is trained to obtain the trained electromagnetic effect influence sub-model.
6. The environmental factor compensation method for the gallium nitride Hall current sensor according to claim 5, characterized in that, The step of inputting the measured output voltage and current environmental conditions into a trained environmental error compensation model to obtain the current measurement compensation amount corresponding to the measured output voltage and current environmental conditions includes: The measured output voltage, current temperature, and current humidity are input into the trained temperature-humidity joint influence sub-model to obtain the first current measurement compensation amount. The measured output voltage and the current electromagnetic interference intensity are input into the trained electromagnetic effect influence sub-model to obtain the second current measurement compensation amount. Input the first current measurement compensation amount and the second current measurement compensation amount into the preset temperature-humidity-electromagnetic effect coupling formula to obtain the intrinsic current measurement compensation amount corresponding to the current environmental conditions. The sum of the intrinsic current measurement compensation and the device measurement error corresponding to the current environmental conditions is calculated to obtain the current measurement compensation corresponding to the current environmental conditions.
7. The environmental factor compensation method for a gallium nitride Hall current sensor according to claim 6, characterized in that, Before inputting the first current measurement compensation amount and the second current measurement compensation amount into a preset temperature-humidity-electromagnetic effect coupling formula to obtain the intrinsic current measurement compensation amount corresponding to the current environmental conditions, the method further includes: Based on the multiple sets of first environmental condition-current measurement error data and the multiple sets of first environmental condition-current measurement error data, polynomial fitting is performed to obtain the temperature-humidity-electromagnetic effect coupling formula.
8. An environmental factor compensation device for a gallium nitride Hall current sensor, characterized in that, include: The acquisition module is used to acquire the measured output voltage of the gallium nitride Hall current sensor under the current environmental conditions; wherein, the environmental conditions include temperature, humidity and electromagnetic interference intensity; The mapping module is used to input the measured output voltage and the current environmental conditions into a trained environmental error compensation model to obtain the current measurement compensation amount corresponding to the measured output voltage and the current environmental conditions; wherein, the environmental error compensation model is used to characterize the mapping relationship between the current measurement error of the gallium nitride Hall current sensor and various environmental conditions; The compensation module is used to compensate the output current corresponding to the measured output voltage based on the current measurement compensation amount, so as to obtain an accurate current measurement value.
9. The environmental factor compensation device for the gallium nitride Hall current sensor according to claim 8, characterized in that, The mapping module is specifically used for: Before inputting the measured output voltage and current environmental conditions into the trained environmental error compensation model to obtain the current measurement compensation amount corresponding to the measured output voltage and current environmental conditions, the current measurement error of the gallium nitride Hall current sensor under various environmental conditions is obtained through experiments, and multiple sets of environmental condition-current measurement error data are obtained. Based on the multiple sets of environmental condition-current measurement error data, the initial environmental error compensation model is trained to obtain the trained environmental error compensation model.
10. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 7.