A temperature error compensation method and system for a strong electric pulse measurement system

Abstract

The present application provides a temperature error compensation method and system for a high-voltage pulse measurement system, which belongs to the field of pulse power technology. The method includes: according to the device temperature coefficient function and the interference weight ratio identification, the influence of the device on the comprehensive error of the output of the high-voltage pulse measurement system to be compensated is analyzed, and the key components of the system are identified; using the temperature coefficient function of the key component as input, with the minimum root mean square of the temperature coefficient in the system operation domain as the goal, a first deep convolutional neural network is used to optimize the allocation of the temperature coefficient of the key component; according to the optimal temperature coefficient of the allocated key component, the actual temperature coefficient of the key component is adjusted through a second deep convolutional neural network using temperature sensors and programmable devices; based on the difference between the actual temperature coefficient of the key component and the optimal temperature coefficient of the allocated key component, the overall output temperature of the measurement system is compensated. The present application realizes effective compensation of the temperature coefficient of the measurement system in the entire temperature operation domain.

Description

Technical Field

[0001] The present application belongs to the field of pulse power technology, and more specifically, relates to a temperature error compensation method and system for a strong electric pulse measurement system. Background Art

[0002] Pulse power technology is widely used in nuclear physics, accelerators, lasers, electromagnetic emission and other technical fields, and also has great potential in chemical engineering, environmental engineering and medical fields. Reliability and precision are important guarantees for the performance of pulse power equipment, and it must be ensured that it can still operate stably in extreme environments or under high-intensity use. The realization of high reliability and high precision depends heavily on the stable operation of the measurement system in extreme environments.

[0003] Devices, circuit boards or materials in the measurement system will change parameters and performance due to temperature changes. Especially after experiencing drastic temperature changes, temperature stress may even cause some devices to fail, resulting in a decrease in the accuracy of the measurement system. In addition, when high-end electromagnetic equipment is deployed in a mobile manner, it will be transported thousands of kilometers in a short period of time, and its operating temperature will vary greatly. In addition, when electromagnetic equipment is running at a repetitive frequency, a large amount of electrical energy is released quickly and partially converted into heat energy. The operating status of the equipment under different working conditions will also significantly affect the operating temperature of the measurement system.

[0004] In order to reduce the impact of ambient temperature on the accuracy, sensitivity and measurement stability of the measurement system, it is necessary to clarify the influence of temperature on the system output characteristics and perform temperature compensation on the output results to reduce the impact of temperature on the measurement system. The existing temperature compensation methods for measurement systems mostly use thermistor networks for overall compensation, that is, the output is compensated by a reverse proportional amplifier circuit that is opposite to the system temperature characteristics, or only the temperature sensitive device in the system is connected in series with a thermistor for error compensation. However, as the measurement system becomes increasingly complex, the temperature error of key components in the system has a significantly increased impact on the measurement results. At the same time, the components are affected by temperature and show nonlinear characteristics. It is difficult to accurately compensate for the temperature error in the temperature operating domain of the measurement system using the existing temperature compensation methods, which seriously restricts the application and accuracy of the measurement system in a large temperature range. Summary of the invention

[0005] In view of the defects of the prior art, the purpose of this application is to provide a temperature error compensation method and system for a high-voltage pulse measurement system, aiming to solve the problem that the existing temperature compensation method is difficult to accurately compensate for the temperature error in the temperature operating domain of the high-voltage pulse measurement system, which seriously restricts the application and accuracy of the high-voltage pulse measurement system in a large temperature range.

[0006] To achieve the above objectives, in a first aspect, the present application provides a temperature error compensation method for a high-voltage pulse measurement system, comprising the following steps:

[0007] Step S1: Analyze the influence of the device on the comprehensive error of the output of the high-voltage pulse measurement system to be compensated according to the device temperature coefficient function and the interference weight ratio, and identify the key components of the system; wherein the device is a device of the high-voltage pulse measurement system to be compensated;

[0008] Step S2: Taking the temperature coefficient function of the key components as input and minimizing the root mean square of the temperature coefficient in the system operation domain as the goal, a first deep convolutional neural network is used to optimize the allocation of the temperature coefficients of the key components to obtain the optimal temperature coefficients of the allocated key components;

[0009] Step S3: According to the optimal temperature coefficient of the assigned key components, using temperature sensors and programmable devices, the actual temperature coefficient of the programmable devices in the key components is adjusted through the second deep convolutional neural network, so that the actual temperature coefficient of the key components approaches the optimal temperature coefficient of the assigned key components; based on the difference between the actual temperature coefficient of the key components and the optimal temperature coefficient of the assigned key components, the overall output temperature of the high-voltage pulse measurement system to be compensated is compensated.

[0010] Further preferably, step S1 specifically includes the following steps:

[0011] Continuously adjust the operating temperature of the high-electric pulse measurement system to be compensated according to the system temperature operation domain of the high-electric pulse measurement system to be compensated;

[0012] The strong pulse current signal is input into the reference strong electric pulse measurement system and the strong electric pulse measurement system to be compensated, and the temperature coefficient function and the interference weight ratio of each device are obtained according to the actual output signal of the strong electric pulse measurement system to be compensated, the reference signal output by the reference strong electric pulse measurement system and the working temperature of the strong electric pulse measurement system to be compensated; wherein the reference strong electric pulse measurement system is always at room temperature;

[0013] According to the device temperature coefficient function and the interference weight ratio, the error synthesis model is used to analyze the impact of each device temperature coefficient on the comprehensive error of the system output, and a normalized evaluation is performed to select key devices.

[0014] Further preferably, in step S2, the first deep convolutional neural network is corrected based on the system output comprehensive error and the system error synthesis model.

[0015] Further preferably, step S3 specifically includes the following steps:

[0016] Step S3.1: Obtain the operating temperature through the temperature sensor and convert it into an analog voltage signal, and then convert it into a voltage digital signal through an analog-to-digital converter;

[0017] Step S3.2: using a second deep convolutional neural network to receive the voltage digital signal, obtain the real-time operating temperature, output a digital control signal, and control the temperature coefficient of the programmable device in the key device; wherein the second deep convolutional neural network is trained with the influence of different operating temperatures on the voltage digital signal, so that the second deep convolutional neural network obtains the influence of the operating temperature on the voltage digital signal;

[0018] Step S3.3: Collect the actual temperature coefficient of the key component after the temperature coefficient adjustment, based on the difference between the actual temperature coefficient of the key component and the optimal temperature coefficient of the assigned key component, eliminate the difference through the digital compensation signal, and convert the digital compensation signal into an analog compensation signal to obtain the actual output signal of the high-voltage pulse measurement system after temperature compensation.

[0019] Further preferably, after acquiring the key components in step S1, the system error synthesis model is simplified.

[0020] Further preferably, in step S1, the error synthesis model uses Monte Carlo simulation to comprehensively analyze the impact of fluctuations in device characteristics, circuit characteristics and system characteristics introduced by device temperature coefficient on the comprehensive error of the output of the high-voltage pulse measurement system to be compensated, wherein the impact of the comprehensive error of the output of the high-voltage pulse measurement system to be compensated includes measurement sensitivity, linearity, stability and resolution.

[0021] In a second aspect, the present application provides a temperature error compensation system for a strong electric pulse measurement system, including: a system key component identification module, an optimal temperature coefficient allocation module and a temperature compensation module;

[0022] The system key component identification module is used to identify the key components of the system according to the component temperature coefficient function and the interference weight ratio, analyze the impact of the component on the comprehensive error of the output of the high-voltage pulse measurement system to be compensated, and identify the key components of the system; wherein the component is a component of the high-voltage pulse measurement system to be compensated;

[0023] The optimal temperature coefficient allocation module is used to use the temperature coefficient function of the key components as input, with the goal of minimizing the root mean square of the temperature coefficient in the system operation domain, and use the first deep convolutional neural network to optimize the allocation of the temperature coefficients of the key components to obtain the optimal temperature coefficients of the allocated key components;

[0024] The temperature compensation module is used to adjust the actual temperature coefficient of the key components according to the optimal temperature coefficient of the assigned key components, using temperature sensors and programmable devices, through the second deep convolutional neural network, so that the actual temperature coefficient of the key components approaches the optimal temperature coefficient of the assigned key components; based on the difference between the actual temperature coefficient of the key components and the optimal temperature coefficient of the assigned key components, the overall output temperature of the high-voltage pulse measurement system to be compensated is compensated.

[0025] Further preferably, the system key component identification module includes a reference strong electric pulse measurement system, a temperature and humidity chamber, a strong pulse power supply and a data processing unit;

[0026] The strong pulse power supply is connected to the reference strong electric pulse measurement system and the strong electric pulse measurement system to be compensated through the Rogowski coil, and is used to input the strong pulse current signal to the reference strong electric pulse measurement system and the strong electric pulse measurement system to be compensated;

[0027] The reference strong electric pulse measurement system is always in a room temperature environment and is used to provide a reference signal;

[0028] The strong electric pulse measurement system to be compensated is located in the temperature and humidity chamber and is used to obtain the actual output signal at the working temperature;

[0029] The temperature and humidity chamber is used to adjust the operating temperature of the high-voltage pulse measurement system to be compensated according to the system temperature operating domain, and to test the influence of each component on the comprehensive error of the system output;

[0030] The data processing unit is used to obtain the temperature coefficient function and interference weight ratio of each component according to the actual output signal of the high-electric pulse measurement system to be compensated, the reference signal output by the reference high-electric pulse measurement system and the operating temperature of the high-electric pulse measurement system to be compensated, adopt the error synthesis model to analyze the influence of the temperature coefficient of each component on the comprehensive error of the system output, perform normalized evaluation, and select key components.

[0031] Further preferably, the temperature compensation module comprises: a temperature sensor, an analog-to-digital converter, a microprocessor and a digital-to-analog converter connected in sequence; the other output end of the microprocessor is connected to the programmable device in the key device; the output end of the key device is connected to the other input end of the analog-to-digital converter;

[0032] The temperature sensor is used to obtain the working temperature and convert it into an analog voltage signal;

[0033] The analog-to-digital converter is used to convert the analog voltage signal into a voltage digital signal;

[0034] The microprocessor is embedded with a second deep convolutional neural network, which is used to obtain the real-time operating temperature according to the voltage digital signal received at the input end of the second deep convolutional neural network, and output a digital control signal to control the temperature coefficient of the programmable device in the key device; wherein the second deep convolutional neural network is trained with the influence of different operating temperatures on the voltage digital signal, so that the second deep convolutional neural network obtains the influence law of the operating temperature on the voltage digital signal;

[0035] The analog-to-digital converter is used to collect the actual temperature coefficient of the key components after temperature coefficient adjustment;

[0036] The microprocessor is used to eliminate the difference through a digital compensation signal based on the difference between the actual temperature coefficient of the key component and the optimal temperature coefficient of the assigned key component;

[0037] The digital-to-analog converter is used to convert the digital compensation signal into an analog compensation signal to obtain the actual output signal of the strong electric pulse measurement system after temperature compensation.

[0038] Further preferably, the error synthesis model in the data processing unit adopts Monte Carlo simulation to comprehensively analyze the influence of fluctuations in device characteristics, circuit characteristics and system characteristics introduced by device temperature coefficient on the comprehensive error of the output of the high-voltage pulse measurement system to be compensated; wherein, the influence of the comprehensive error of the output of the high-voltage pulse measurement system to be compensated includes measurement sensitivity, linearity, stability and resolution.

[0039] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the prior art:

[0040] The present application provides a temperature error compensation method for a high-voltage pulse measurement system. The method analyzes the influence of the device on the comprehensive error of the output of the high-voltage pulse measurement system to be compensated according to the device temperature coefficient function and the interference weight ratio identification. By determining the key components and the device-system error synthesis model, the comprehensive error of the system output and the temperature characteristics are comprehensively considered (wherein the error synthesis model uses Monte Carlo simulation to comprehensively analyze the influence of the fluctuations of the device characteristics, circuit characteristics and system characteristics introduced by the device temperature coefficient on the comprehensive error of the output of the high-voltage pulse measurement system to be compensated). The method can clarify the mechanism and influence law of large-span high and low temperatures on the high-voltage pulse measurement system.

[0041] The present application provides a temperature error compensation method for a high-voltage pulse measurement system. Through a system error synthesis model, it can quantitatively analyze the influence of the temperature coefficient of key components on the overall temperature coefficient of the system, and give the optimal temperature coefficient of the key components based on the first deep convolutional neural network, so as to minimize the comprehensive error in the entire temperature operation domain of the system.

[0042] The present application provides a temperature error compensation method for a high-power pulse measurement system, wherein intelligent adjustment and compensation of the temperature coefficients of key components of the high-power pulse measurement system are realized through a second deep convolutional neural network and a programmable device, and wide-range adaptation of the temperature coefficient within the full temperature operating domain of the system is realized.

[0043] The present application provides a temperature error compensation method for a high-voltage pulse measurement system, which is divided into two steps to perform temperature compensation on the high-voltage pulse measurement system to be compensated. The first step is to adjust the actual temperature coefficient of the programmable device in the key device through the second deep convolutional neural network, so that the actual temperature coefficient of the key device approaches the optimal temperature coefficient of the allocated key device; the second step is to compensate for the overall output temperature of the high-voltage pulse measurement system to be compensated based on the difference between the actual temperature coefficient of the key device and the optimal temperature coefficient of the allocated key device, thereby realizing effective compensation of the temperature coefficient of the measurement system in the entire temperature operating range. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flowchart of a temperature error compensation method for a strong electric pulse measurement system in a large temperature range provided in an embodiment of the present application;

[0045] Figure 2 It is a typical experimental circuit of the temperature error compensation method of the strong electric pulse measurement system with a large temperature span provided in the embodiment of the present application;

[0046] Figure 3 It is a temperature test cycle of a temperature error compensation method of a strong electric pulse measurement system with a large temperature span provided in an embodiment of the present application;

[0047] Figure 4 This is a basic structure diagram of a typical measurement system of a temperature error compensation method for a strong electric pulse measurement system with a large temperature span provided in an embodiment of the present application;

[0048] Figure 5 It is a schematic diagram of the temperature coefficient adjustment and temperature compensation structure of the temperature error compensation method of the strong electric pulse measurement system with a large temperature span provided in the embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The term "and / or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.

[0051] The terms “first”, “second” and the like in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of the objects.

[0052] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0053] In the description of the embodiments of the present application, unless otherwise specified, “plurality” means two or more than two.

[0054] Next, the technical solutions provided in the embodiments of the present application are introduced.

[0055] The present application provides a method and system for temperature error compensation of a high-voltage pulse measurement system with a large temperature range. The purpose is to determine the influence of the temperature coefficient of key components of the high-voltage pulse measurement system on the overall temperature characteristics of the output of the high-voltage pulse measurement system, and quantitatively analyze the system temperature error through device-system error synthesis, and optimally allocate the temperature coefficients of key components according to the high-voltage pulse measurement system and device characteristics, and achieve wide-range adjustment and compensation of the temperature characteristics of key components through deep learning networks and programmable devices. Through overall optimization allocation and intelligent adjustment and compensation, the temperature error compensation of the measurement system is guided, so that the comprehensive error of the high-voltage pulse measurement system output in the full temperature operating domain is minimized.

[0056] like Figure 1 As shown, the embodiment of the present application provides a temperature error compensation method for a strong electric pulse measurement system in a large temperature range, which specifically includes the following steps:

[0057] Step 1: Identify the key components of the strong electric pulse measurement system: Identify the components based on the temperature coefficient function and interference weight ratio of the components, analyze the impact of the components on the comprehensive error of the strong electric pulse measurement system output through the system error synthesis model, and identify the key components of the system;

[0058] Step 2: Optimize the distribution of device temperature coefficients: Based on the temperature coefficient function of key components as input and the goal of minimizing the comprehensive error of the output of the high-voltage pulse measurement system to be compensated, the first deep convolutional neural network is used to optimize the distribution of key component temperature coefficients and allocate the optimal key component temperature coefficients;

[0059] Step 3: System temperature compensation: According to the optimal temperature coefficient of the assigned key components, use temperature sensors and programmable devices to adjust the actual temperature coefficient of the key components through the second deep convolutional neural network, so that the actual temperature coefficient of the key components approaches the optimal temperature coefficient of the assigned key components. Based on the difference between the actual temperature coefficient of the key components and the optimal temperature coefficient of the assigned key components, the overall output temperature of the system is compensated to reduce the impact of temperature on the system.

[0060] More specifically, in the first step, key components are obtained; Figure 2 The temperature test platform shown includes: a strong pulse power supply, a reference strong electric pulse measurement system, a temperature and humidity chamber and a data recording module; the strong pulse power supply inputs the strong pulse current signal into the reference strong electric pulse measurement system and the strong electric pulse measurement system to be calibrated through the Rogowski coil; the reference strong electric pulse measurement system is always in a room temperature environment to provide a reference signal; the strong electric pulse measurement system to be compensated is located in the temperature and humidity chamber; wherein the temperature and humidity chamber adjusts the operating temperature of the strong electric pulse measurement system to be compensated according to the system temperature operating domain, and tests the influence of each component on the system output characteristics; in this embodiment, the temperature adjustment method of the measurement system is as follows Figure 3 As shown, the national standard temperature test method is adopted, and the temperature adjustment range is -10℃~30℃;

[0061] The data recording module is used to record and process the reference signal, the actual signal output by the high-voltage pulse measurement system to be calibrated, and the ambient temperature of the high-voltage pulse measurement system to be calibrated, and obtain the temperature coefficient function of each device; according to the device temperature coefficient function, adjust the temperature coefficient of the high-voltage pulse measurement system device, use the error synthesis model to analyze the impact of the temperature coefficient of each device on the system output, and perform a normalized comprehensive evaluation, and select the device with a significant impact on the system output as the key device of the system;

[0062] More specifically, Monte Carlo simulation is used to comprehensively analyze the impact of fluctuations in device characteristics, circuit characteristics, and system characteristics on the system's comprehensive error, and the system error synthesis model is simplified by selecting key components.

[0063] Among them, the comprehensive error of the system error synthesis model considers key parameters such as measurement sensitivity, linearity, stability and resolution;

[0064] The second step is as follows: the first deep convolutional neural network is trained through the influence of the temperature coefficient of the key components of the system on the comprehensive error of the strong electric pulse measurement system, and the first deep convolutional neural network is corrected based on the system output and the physical prior model of the temperature coefficient of the key components (system error synthesis model). The optimal distribution of the temperature coefficient of the key components is determined based on the trained first deep convolutional neural network, so that the root mean square of the temperature coefficient in the system operation domain is minimized;

[0065] In this embodiment, Figure 4 It is a strong electric pulse measurement system, whose key components are coil collection resistor, integrator capacitor and resistor in the integrator; the temperature coefficients of these three components are distributed in the range of -10℃~30℃, and the three components show linear characteristics to temperature changes in this range, and the optimal distribution coefficient is that the temperature coefficients of the three components are all 0;

[0066] Further preferably, the operating temperature is obtained by a temperature sensor and converted into an analog voltage signal, which is converted into a voltage digital signal by an ADC of a signal processing module and transmitted to a microprocessor. The microprocessor has a built-in second deep convolutional neural network, and uses experiments to obtain the influence of the operating temperature on the voltage digital signal to train the deep learning network, obtain the influence of temperature on the voltage digital signal, and obtain the real-time operating temperature of the environment according to the received digital signal, output a digital control signal, control the programmable device parameters to change with temperature, and realize temperature coefficient adjustment;

[0067] More specifically, the schematic diagram of the temperature coefficient adjustment and temperature compensation structure is as follows: Figure 5 As shown, the integral capacitor C J Using IXYS NCD2100 digital programmable capacitor, the capacitance value can be set by simple two-wire serial longitudinal. The capacitance value can be adjusted arbitrarily from 6.6pF to 37.553pF through the built-in switch. The adjustment accuracy is 0.063pF and the adjustment progress is about 1%. The inverse proportional amplification resistor R s The programmable resistor MCP4017T-104E / LT is used. In this embodiment, a model with a maximum resistance of 5kΩ and an 8-bit adjustment step is selected. The adjustment progress is about 1%, and the adjustment step is 50Ω. For the 20kΩ main amplifier resistor R2, the adjustment range is 12.5%, and the adjustment step progress is 0.25%, which can effectively achieve temperature compensation over the full temperature range;

[0068] The signal processing module collects the variation law of the system output parameters with temperature after the temperature coefficient is adjusted, eliminates the overall temperature error of the system through digital compensation in the signal processing module, and converts the overall compensated digital signal output by the digital processing module into an output analog signal through DAC;

[0069] More specifically, in this embodiment, due to the limitation of the adjustment accuracy of programmable capacitors and programmable resistors, within the temperature variation range of 3°C, the capacitance value offset caused by temperature is less than 0.063pF, resulting in a deviation between the actual temperature compensation coefficient and the optimal temperature coefficient. The system output is affected by temperature within a small range. The output voltage is collected using a 12-bit ADC converter, and the temperature error caused by the temperature coefficient deviation is compensated. The compensation accuracy can reach 0.025%, which is much smaller than the 1% adjustment deviation of the adjustable capacitor, and can effectively improve the temperature compensation accuracy.

[0070] In summary, compared with the prior art, the present application has the following advantages:

[0071] This application determines the key components and the system error synthesis model, comprehensively considers the overall system error and temperature characteristics, and can clarify the mechanism and influence of large-span high and low temperatures on the strong electric pulse measurement system.

[0072] Through the system error synthesis model, this application can quantitatively analyze the influence of the temperature coefficient of key components on the overall temperature coefficient of the system, and give the optimal temperature coefficient of key components based on the deep learning network, so as to minimize the comprehensive error in the full temperature operation domain of the system.

[0073] This application uses deep learning networks and programmable devices to achieve intelligent adjustment and compensation of the temperature coefficients of key components in a high-voltage pulse measurement system, and realizes wide-range adaptation of the temperature coefficients within the full temperature operating domain of the system.

[0074] The present application provides measurement of overall optimized distribution and intelligent compensation of temperature coefficient of a strong electric pulse measurement system, thereby realizing effective compensation of temperature coefficient in the full temperature operating range of the measurement system.

[0075] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0076] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0077] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A temperature error compensation method for a strong electric pulse measurement system, characterized in that: The following steps are involved: Step S1: Analyze the influence of the device on the comprehensive error of the output of the high-voltage pulse measurement system to be compensated according to the device temperature coefficient function and the interference weight ratio, and identify the key components of the system; wherein the device is a device of the high-voltage pulse measurement system to be compensated; Step S2: Taking the temperature coefficient function of the key components as input and minimizing the comprehensive error of the output of the high-voltage pulse measurement system to be compensated as the goal, a first deep convolutional neural network is used to optimize the allocation of the temperature coefficients of the key components to obtain the optimal temperature coefficients of the allocated key components; Step S3: According to the optimal temperature coefficient of the allocated key device, the actual temperature coefficient of the programmable device in the key device is adjusted by using the temperature sensor and the programmable device, so that the actual temperature coefficient of the key device approaches the optimal temperature coefficient of the allocated key device; based on the difference between the actual temperature coefficient of the key device and the optimal temperature coefficient of the allocated key device, the overall output temperature of the high-voltage pulse measurement system to be compensated is compensated; Wherein, step S1 specifically includes the following steps: Continuously adjust the operating temperature of the high-electric pulse measurement system to be compensated according to the system temperature operation domain of the high-electric pulse measurement system to be compensated; Inputting a strong pulse current signal into a reference strong electric pulse measurement system and a strong electric pulse measurement system to be compensated, and obtaining a temperature coefficient function of each device according to an actual output signal of the strong electric pulse measurement system to be compensated, a reference signal output by the reference strong electric pulse measurement system, and an operating temperature of the strong electric pulse measurement system to be compensated; According to the device temperature coefficient function, adjust the temperature coefficient of the device in the high-voltage pulse measurement system to be compensated, use the error synthesis model to analyze the influence of the temperature coefficient of each device on the output of the high-voltage pulse measurement system to be compensated, and perform a normalized comprehensive evaluation to select the device with a significant influence on the output of the high-voltage pulse measurement system to be compensated as the key device of the system; Step S3 specifically includes the following steps: Step S3.1: Obtain the operating temperature through the temperature sensor and convert it into an analog voltage signal, and then convert it into a voltage digital signal through an analog-to-digital converter; Step S3.2: using a second deep convolutional neural network to receive the voltage digital signal, and training the second deep convolutional neural network with the influence of different operating temperatures on the voltage digital signal, so that the second deep convolutional neural network obtains the influence law of the operating temperature on the voltage digital signal, obtains the real-time operating temperature according to the output of the second deep convolutional neural network, outputs a digital control signal, controls the temperature coefficient of the programmable device in the key device, and makes the actual temperature coefficient of the key device approach the optimal temperature coefficient of the allocated key device; Step S3.3: Collect the actual temperature coefficient of the key component after the temperature coefficient adjustment, based on the difference between the actual temperature coefficient of the key component and the optimal temperature coefficient of the assigned key component, eliminate the difference through the digital compensation signal, and convert the signal compensated by the digital compensation signal into an analog signal to obtain the actual output signal of the high-voltage pulse measurement system after temperature compensation.

2. The temperature error compensation method according to claim 1, characterized in that: In step S2, the first deep convolutional neural network is corrected based on the system output comprehensive error and the system error synthesis model.

3. The temperature error compensation method according to claim 1, characterized in that: In step S1, the error synthesis model uses Monte Carlo simulation to comprehensively analyze the impact of fluctuations in device characteristics, circuit characteristics, and system characteristics introduced by device temperature coefficients on the comprehensive error of the output of the high-voltage pulse measurement system to be compensated; wherein, the impact of the comprehensive error of the output of the high-voltage pulse measurement system to be compensated includes measurement sensitivity, linearity, stability, and resolution.

4. A temperature error compensation system for a strong electric pulse measurement system, characterized in that: include: System key component identification module, optimal temperature coefficient allocation module and temperature compensation module; The system key component identification module is used to identify the key components of the system according to the component temperature coefficient function and the interference weight ratio, analyze the impact of the component on the comprehensive error of the output of the high-voltage pulse measurement system to be compensated, and identify the key components of the system; wherein the component is a component of the high-voltage pulse measurement system to be compensated; The optimal temperature coefficient allocation module is used to use the temperature coefficient function of the key components as input, with the goal of minimizing the root mean square of the temperature coefficient in the system operation domain, and use the first deep convolutional neural network to optimize the allocation of the temperature coefficients of the key components to obtain the optimal temperature coefficients of the allocated key components; The temperature compensation module is used to adjust the actual temperature coefficient of the key device according to the optimal temperature coefficient of the assigned key device by using the temperature sensor and the programmable device, so that the actual temperature coefficient of the key device approaches the optimal temperature coefficient of the assigned key device; based on the difference between the actual temperature coefficient of the key device and the optimal temperature coefficient of the assigned key device, the overall output temperature of the high-voltage pulse measurement system to be compensated is compensated; Among them, the system key component identification module includes: benchmark strong electric pulse measurement system, temperature and humidity chamber, strong pulse power supply and data processing unit; The strong pulse power supply is connected to the reference strong electric pulse measurement system and the strong electric pulse measurement system to be compensated through the Rogowski coil, and is used to input the strong pulse current signal to the reference strong electric pulse measurement system and the strong electric pulse measurement system to be compensated; The reference strong electric pulse measurement system is always in a room temperature environment and is used to provide a reference signal; The strong electric pulse measurement system to be compensated is located in the temperature and humidity chamber and is used to obtain the actual output signal at the working temperature; The temperature and humidity chamber is used to adjust the operating temperature of the high-voltage pulse measurement system to be compensated according to the system temperature operating domain, and to test the influence of each component on the comprehensive error of the system output; The data processing unit is used to obtain the temperature coefficient function of each device according to the actual output signal of the high-electric pulse measurement system to be compensated, the reference signal output by the reference high-electric pulse measurement system, and the operating temperature of the high-electric pulse measurement system to be compensated; according to the device temperature coefficient function, the temperature coefficient of the device of the high-electric pulse measurement system to be compensated is adjusted, and the error synthesis model is used to analyze the influence of the temperature coefficient of each device on the output of the high-electric pulse measurement system to be compensated, and a normalized comprehensive evaluation is performed, and the device with a significant influence on the output of the high-electric pulse measurement system to be compensated is selected as the key device of the system; The temperature compensation module includes: a temperature sensor, an analog-to-digital converter, a microprocessor and a digital-to-analog converter connected in sequence; the other output end of the microprocessor is connected to the programmable device in the key device; the output end of the key device is connected to the other input end of the analog-to-digital converter; The temperature sensor is used to obtain the working temperature and convert it into an analog voltage signal; The analog-to-digital converter is used to convert the analog voltage signal into a voltage digital signal; The microprocessor is embedded with a second deep convolutional neural network, which is used to train the second deep convolutional neural network based on the voltage digital signal received at the input end of the second deep convolutional neural network and the influence of different operating temperatures on the voltage digital signal, so that the second deep convolutional neural network obtains the influence law of the operating temperature on the voltage digital signal, obtains the real-time operating temperature according to the output of the second deep convolutional neural network, outputs a digital control signal, controls the temperature coefficient of the programmable device in the key device, and makes the actual temperature coefficient of the key device approach the optimal temperature coefficient of the allocated key device; The analog-to-digital converter is used to collect the actual temperature coefficient of the key components after temperature coefficient adjustment; The microprocessor is used to eliminate the difference through a digital compensation signal based on the difference between the actual temperature coefficient of the key component and the optimal temperature coefficient of the assigned key component; The digital-to-analog converter is used to convert the signal compensated by the digital compensation signal into an analog signal to obtain the actual output signal of the strong electric pulse measurement system after temperature compensation.

5. The temperature error compensation system according to claim 4, characterized in that: The error synthesis model in the data processing unit uses Monte Carlo simulation to comprehensively analyze the impact of fluctuations in device characteristics, circuit characteristics and system characteristics introduced by device temperature coefficient on the output comprehensive error of the high-voltage pulse measurement system to be compensated; among them, the impact of the output comprehensive error of the high-voltage pulse measurement system to be compensated includes measurement sensitivity, linearity, stability and resolution.

Images