A Temperature Measurement Error Correction Method Based on Hemispherical Resonator

Abstract

The present application discloses a temperature measurement error correction method based on a hemispherical resonator. By obtaining the current measurement data of the hemispherical resonator in the current measurement environment and uploading it to the data storage center and the fusion neural network model, the temperature compensation multi-layer perceptron unit of the fusion neural network model outputs the temperature-frequency compensation value of the hemispherical resonator, and the aging compensation long short-term memory network unit of the fusion neural network model outputs the aging-frequency compensation value of the hemispherical resonator. The fusion layer of the fusion neural network model fuses the temperature-frequency compensation value and the aging-frequency compensation value and then outputs the frequency adjustment value of the hemispherical resonator. The compensated temperature value is obtained according to the frequency adjustment value of the hemispherical resonator. At the same time, temperature-frequency compensation and aging-frequency compensation are performed on the hemispherical resonator during the temperature measurement process, thereby improving the compensation accuracy of the hemispherical resonator during temperature measurement and effectively improving the measurement accuracy of the hemispherical resonator.

Description

Technical Field

[0001] This application relates to the technical field of sensor measurement, and particularly to a temperature measurement error correction method based on a hemispherical resonator. Background Art

[0002] As a high-precision sensor element, the hemispherical resonator has a wide range of applications in the fields of inertial navigation, precision measurement, etc. Its working principle is based on vibration characteristics, and physical quantity information is obtained by detecting vibration parameters. However, the performance of the hemispherical resonator is significantly affected by temperature, seriously affecting measurement accuracy and reliability. Therefore, currently, during the working process of the hemispherical resonator, it is necessary to compensate for the errors caused by temperature to ensure the accuracy of the measurement of the hemispherical resonator. However, during the use of the hemispherical resonator, it will gradually age, and the aging of the hemispherical resonator will also affect the measurement accuracy. Then, the existing temperature measurement error correction methods for hemispherical resonators only compensate for the errors caused by the temperature of the hemispherical resonator, without considering the temperature change of the measurement environment of the hemispherical resonator and the aging of the hemispherical resonator caused by long-term use. If only the errors caused by temperature are compensated without considering the aging problem of the hemispherical resonator, it is easy to lead to a reduction in compensation accuracy and inaccurate error correction, and at the same time, it also leads to a reduction in the temperature measurement accuracy of the hemispherical resonator. Summary of the Invention

[0003] This application provides a temperature measurement error correction method based on a hemispherical resonator to solve the problem of low temperature measurement accuracy of the current hemispherical resonator under the influence of temperature and after aging.

[0004] To solve the above technical problems, in a first aspect, this application provides a temperature measurement error correction method based on a hemispherical resonator,

[0005] Obtain the current measurement data of the hemispherical resonator in the current measurement environment and upload it to the data storage center and the fusion neural network model; the current measurement data includes at least one temperature value of the hemispherical resonator in the current measurement environment, the cumulative usage duration of the hemispherical resonator, and the running duration of the hemispherical resonator after the last maintenance;

[0006] The data storage center is used to store the current measurement data and the historical measurement data of the hemispherical resonator;

[0007] The fusion neural network model is an artificial intelligence model trained based on historical measurement data;

[0008] Output the temperature frequency compensation value of the hemispherical resonator through the temperature compensation multi-layer perceptron unit of the fusion neural network model;

[0009] The aging compensation long short-term memory network unit of the fusion neural network model outputs the aging frequency compensation value of the hemispherical resonator;

[0010] The fusion layer of the fusion neural network model fuses the temperature frequency compensation value and the aging frequency compensation value and then outputs the temperature frequency compensation value of the hemispherical resonator;

[0011] The fusion neural network model obtains the compensated temperature value according to the frequency adjustment value of the hemispherical resonator.

[0012] In one embodiment, the method for obtaining the current measurement data of the hemispherical resonator in the current measurement environment and uploading it to the data storage center and the fusion neural network model includes:

[0013] Obtain the temperature values at different positions in the current measurement environment of the hemispherical resonator and upload them to the data storage center and the fusion neural network model;

[0014] Obtain the cumulative usage duration of the hemispherical resonator in the current measurement environment and upload it to the data storage center and the fusion neural network model.

[0015] In one embodiment, the method for outputting the temperature frequency compensation value of the hemispherical resonator through the temperature compensation multi-layer perceptron unit of the fusion neural network model includes:

[0016] Input at least one temperature value as an input node in the first input layer;

[0017] Each neuron in the hidden layer receives different temperature values from the first input layer and outputs the temperature data value after weighted average summation according to the preset weight to the temperature compensation output layer;

[0018] The temperature compensation output layer outputs the temperature frequency compensation value after weighted average summation of the temperature data value.

[0019] In one embodiment, the formula for the temperature data value obtained by weighted average summation according to the preset weight is:

[0020] S 1 =W 1 T 1 +W 2 T 2 +W 3 T 3 +······+W N T N , T 1 , T 2 , T 3 , T N are temperature values, W 1 , W2 , W 3 , W N is T 1 , T 2 , T 3 , T N are the corresponding weights respectively.

[0021] In one embodiment, the calculation formula for outputting the temperature frequency compensation value after weighted averaging and summing the temperature data values is: yt = V 1 S 1 + V 2 S 2 + V 3 S 3 + ······ + V N S N , S 1 , S 2 , S 3 , S N are the temperature data values output by the hidden layer, and V 1 , V 2 , V 3 , V N are the corresponding weights for S 1 , S 2 , S 3 , S N respectively.

[0022] In one embodiment, the method for outputting the aging frequency compensation value of the hemispherical resonator through the aging compensation long short-term memory network unit of the fusion neural network model includes:

[0023] Input the cumulative usage duration of the hemispherical resonator and / or the running duration after the last maintenance of the hemispherical resonator into the second input layer;

[0024] The cumulative usage duration of the hemispherical resonator and / or the running duration after the last maintenance of the hemispherical resonator are used as time node data and input into the LSTM layer unit;

[0025] The time node data is processed by the input gate subunit, forget gate subunit, memory unit, and output gate subunit in the LSTM layer unit and outputs at least one aging output value, and the aging output value is output to the aging output layer unit;

[0026] At least one aging output value is weighted and summed in the aging output layer unit to output the aging frequency compensation value.

[0027] In one embodiment, the method for outputting at least one aging output value after the time node data is processed by an input gate sub-unit, a forget gate sub-unit, a memory unit, and an output gate sub-unit in an LSTM layer unit and outputting the aging output value to an aging output layer unit includes:

[0028] Calculating and obtaining an input gate value through the input gate sub-unit;

[0029] Calculating and obtaining a forget gate value through the forget gate sub-unit;

[0030] Calculating a memory unit value through the input gate value and the forget gate value;

[0031] The output gate sub-unit calculates an aging output value according to the time node data and the memory unit value.

[0032] In one embodiment, the method for outputting an aging frequency compensation value after performing weighted summation processing on the at least one aging output value in the aging output layer unit is:

[0033] According to the formula y a = u 1 l 1 + u 2 l 2 + ······ + u n l n , y a is the aging frequency compensation value, l 1 , l 2 , l n are the aging output values, and u 1 , u 2 , u n are the weights corresponding to l 1 , l 2 , l n .

[0034] In one embodiment, in the fusion layer, the frequency adjustment value of the hemispherical resonator is calculated through the formula y = w T yt + w A y a , where w T and w A are the weights of the fusion layer.

[0035] In one embodiment, after the temperature frequency compensation value and the aging frequency compensation value are fused in the fusion layer of the fusion neural network model and the frequency adjustment value of the hemispherical resonator is output, it is determined whether the output frequency adjustment value of the hemispherical resonator is accurate.

[0036] In one embodiment, the method for determining whether the output frequency adjustment value of the hemispherical resonator is accurate is:

[0037] Obtain the true resonator frequency value of the hemispherical resonator without the influence of temperature and aging;

[0038] Obtain the frequency adjustment value of the hemispherical resonator output by the fusion neural network model;

[0039] Determine whether the difference between the true resonator frequency value and the corrected resonator frequency is within a preset threshold;

[0040] If yes, it proves that the frequency adjustment value of the hemispherical resonator is accurate.

[0041] In a second aspect, the present application also provides a computer device, including a processor and a memory, where the memory is used to store a computer program, and when the computer program is executed by the processor, it implements a temperature measurement error correction method based on a hemispherical resonator.

[0042] In a third aspect, the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the temperature measurement error correction method based on a hemispherical resonator.

[0043] Compared with the prior art, the present application has at least the following beneficial effects:

[0044] Through the temperature measurement error correction method based on the hemispherical resonator, the present application obtains the current measurement data of the hemispherical resonator in the current measurement environment and uploads it to the data storage center and the fusion neural network model. The temperature compensation multi-layer perceptron unit of the fusion neural network model outputs the temperature frequency compensation value of the hemispherical resonator, and the aging compensation long short-term memory network unit of the fusion neural network model outputs the aging frequency compensation value of the hemispherical resonator. The fusion layer of the fusion neural network model fuses the temperature frequency compensation value and the aging frequency compensation value and then outputs the frequency adjustment value of the hemispherical resonator. The compensated temperature value is obtained according to the frequency adjustment value of the hemispherical resonator. At the same time, temperature frequency compensation and aging frequency compensation are performed on the hemispherical resonator during the temperature measurement process, thereby improving the compensation accuracy of the hemispherical resonator during temperature measurement, and also effectively improving the measurement accuracy of the hemispherical resonator, making the temperature measurement error smaller. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic flowchart of the temperature measurement error correction method based on a hemispherical resonator shown in an embodiment of the present application;

[0046] Figure 2 It is a schematic structural diagram of the computer device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts belong to the scope of protection of the present application.

[0048] The characteristics of the hemispherical resonator are closely related to temperature and can be used for temperature measurement or auxiliary temperature measurement error correction in specific situations. The hemispherical resonator is commonly made of high-quality quartz material, which has an extremely low thermal expansion coefficient, meaning that when the temperature changes, the physical size and vibration characteristics of the hemispherical resonator change very little. In the field of high-precision inertial navigation and control, such as the hemispherical resonator gyroscope (HRG), the vibration characteristics of the hemispherical resonator are used to measure the angular velocity. Temperature fluctuations will affect the vibration frequency and mode of the hemispherical resonator, thereby introducing errors into the measurement results of the gyroscope. Therefore, from this perspective, the temperature change can be inferred by monitoring the change in the vibration characteristics of the hemispherical resonator.

[0049] However, in the prior art, usually only the change in size caused by thermal expansion and contraction of the hemispherical resonator at different temperatures is considered, which in turn affects the vibration characteristics. By accurately measuring these changes and using a suitable algorithm, the temperature measurement error can be corrected. However, the hemispherical resonator will inevitably age during long-term use. For an aged hemispherical resonator, during a long-term measurement process, its output signal will show greater fluctuations. This is because aging leads to a decrease in the consistency of material properties and may also change the internal stress distribution. Taking the temperature measurement application as an example (inferring temperature by monitoring the change in the vibration characteristics of the resonator), aging causes the resonator signals measured at different times to have significant differences at the same temperature, and cannot stably reflect the true temperature, affecting the stability of the measurement.

[0050] Therefore, the present application compensates the temperature measurement value of the hemispherical resonator from two aspects of temperature and aging. The fusion neural network model can output the frequency adjustment value of the hemispherical resonator that combines the temperature frequency compensation value and the aging frequency compensation value according to the input temperature value of the hemispherical resonator and the cumulative usage duration of the hemispherical resonator. Furthermore, the compensated temperature value can be obtained according to the frequency adjustment value of the hemispherical resonator, not just simply considering the influence of temperature on the measurement result, making the temperature value measured by the hemispherical resonator more accurate.

[0051] Please refer to Figure 1 , the present application provides a method for correcting the temperature measurement error based on a hemispherical resonator,

[0052] S1. Obtain the current measurement data of the hemispherical resonator in the current measurement environment and upload it to the data storage center and the fusion neural network model;

[0053] The current measurement data includes at least one temperature value of the hemispherical resonator in the current measurement environment and the cumulative usage duration of the hemispherical resonator;

[0054] The data storage center is used to store the current measurement data and the historical measurement data of the hemispherical resonator;

[0055] The method for obtaining the current measurement data of the hemispherical resonator in the current measurement environment and uploading it to the data storage center and the fusion neural network model includes:

[0056] S11. Obtain the temperature values at different positions of the hemispherical resonator in the current measurement environment and upload them to the data storage center and the fusion neural network model; the temperature value can be one temperature value or multiple temperature values. The data storage center stores the temperature values for subsequent use;

[0057] S12. Obtain the cumulative usage duration of the hemispherical resonator in the current measurement environment and upload it to the data storage center and the fusion neural network model.

[0058] The fusion neural network model is an artificial intelligence model trained based on historical measurement data; the historical measurement data includes a large number of temperature values, the frequency values output by the hemispherical resonator corresponding to the temperature values, and the corresponding cumulative usage duration of the hemispherical resonator. Through the training of a large amount of data, the accuracy of the fusion neural network model is improved.

[0059] S2. Output the temperature-frequency compensation value of the hemispherical resonator through the temperature compensation multi-layer perceptron unit of the fusion neural network model;

[0060] The method for outputting the temperature-frequency compensation value of the hemispherical resonator through the temperature compensation multi-layer perceptron unit of the fusion neural network model includes:

[0061] S21. Input at least one temperature value as an input node in the first input layer; for example, if there are three temperature sensors at different positions, there will be three nodes in the input layer, corresponding to these three temperature values respectively;

[0062] S22. Each neuron in the hidden layer receives different temperature values from the first input layer and outputs the temperature data value after weighted average summation according to the preset weight to the temperature compensation output layer;

[0063] The hidden layer processes the input temperature value through weighted calculations of neurons and activation functions. Each neuron receives signals from the first input layer or the previous hidden layer, and these signals are multiplied by the corresponding weights and then summed. Taking a temperature compensation multi-layer perceptron unit with two hidden layers as an example, the temperature value of the first input layer is passed to 50 neurons in the first hidden layer. For a certain neuron in the first hidden layer, it multiplies the temperature values T 1 、T 2 、T 3 from three nodes of the input layer (assuming three temperature sensors) with the corresponding weights W 1 、W 2 、W 3 respectively, and then sums them up to obtain.

[0064] After that, this summation result will be processed by a non-linear activation function (such as the ReLU function). If S 1 is greater than 0, the neuron outputs S 1 ; if S 1 is less than 0, it outputs 0. This output result will be used as the input signal for the neurons in the next layer (the second hidden layer), and the neurons in the second hidden layer will repeat the above process of weighted summation and activation function processing to further extract and transform the features in the temperature data, so as to better fit the complex non-linear relationship between temperature and hemispherical resonator parameters, and finally provide more valuable information for the temperature compensation output layer to calculate the temperature frequency compensation value.

[0065] The formula for the temperature data value obtained by weighted average summation according to the preset weights is:

[0066] S 1 =W 1 T 1 +W 2 T 2 +W 3 T 3 +······+W N T N ,T 1 、T 2 、T 3 、T N are temperature values, and W 1 、W 2 、W 3 、W N are the weights corresponding to T 1 、T 2 、T 3 、T N respectively.

[0067] S23. The temperature compensation output layer outputs the temperature frequency compensation value after weighted average summation of the temperature data value.

[0068] The calculation formula for outputting the temperature frequency compensation value after weighted averaging and summing the temperature data values is: yt = V 1 S 1 + V 2 S 2 + V 3 S 3 + ······ + V N S N , S 1 , S 2 , S 3 , S N are the temperature data values output by the hidden layer, and V 1 , V 2 , V 3 , V N are the weights corresponding to S 1 , S 2 , S 3 , S N respectively.

[0069] The temperature compensation output layer has only one node, which will perform a weighted sum of the values of all neurons output by the last hidden layer. The weights here are continuously adjusted and determined through the backpropagation algorithm during the training process. The summation result yt is the output temperature frequency compensation value, which is directly used as the final output of the temperature compensation multi-layer perceptron unit to compensate for the frequency deviation of the hemispherical resonator caused by temperature changes.

[0070] S3. Output the aging frequency compensation value of the hemispherical resonator through the aging compensation long short-term memory network unit of the fusion neural network model;

[0071] The method for outputting the aging frequency compensation value of the hemispherical resonator through the aging compensation long short-term memory network unit of the fusion neural network model includes:

[0072] S31. Input the cumulative usage duration of the hemispherical resonator and / or the running duration after the last maintenance of the hemispherical resonator into the second input layer;

[0073] S32. The cumulative usage duration of the hemispherical resonator and / or the running duration after the last maintenance of the hemispherical resonator are used as time node data and input into the LSTM layer unit;

[0074] S33. The time node data is processed by the input gate subunit, forget gate subunit, memory unit, and output gate subunit in the LSTM layer unit to output at least one aging output value, and the aging output value is output to the aging output layer unit;

[0075] The method for outputting at least one aging output value after processing the time node data through an input gate subunit, a forget gate subunit, a memory unit, and an output gate subunit in an LSTM layer unit and outputting the aging output value to an aging output layer unit includes:

[0076] S331. Calculate and obtain an input gate value through the input gate subunit;

[0077] S332. Calculate and obtain a forget gate value through the forget gate subunit;

[0078] S333. Calculate a memory unit value based on the input gate value and the forget gate value;

[0079] S334. The output gate subunit calculates an aging output value according to the time node data and the memory unit value.

[0080] S34. At least one aging output value undergoes weighted summation processing in the aging output layer unit and then outputs an aging frequency compensation value;

[0081] When the second input layer data (such as the cumulative usage duration of a hemispherical resonator, the running time after the last maintenance) enters the LSTM layer, it will first be simultaneously transmitted to the input gate subunit, the forget gate subunit, and the output gate. For the input gate, it calculates an input gate value based on the second input layer input data and the hidden state at the previous moment. This value determines how much information in the current input data will be added to the memory unit. Assume the input data is x t , for example, the cumulative usage duration of a hemispherical resonator, and the hidden state at the previous moment is h t-1 , through a series of operations of weight matrices, such as i t = σ(W ix x t + W ih h t-1 + b i ), where σ is the sigmoid activation function, W ix , W ih are weight matrices, b i is the bias term, and the calculated i t is the input gate value.

[0082] The forget gate subunit determines which old information in the memory unit will be retained. Similarly, through similar operations, such as f t = σ(W fx x t + W fh h t-1 + b f ), the forget gate value f t is obtained. The memory unit calculates a memory unit value based on the input gate value and the forget gate value, W fx and Wfh is the weight matrix, b f is the bias term of the forget gate;

[0083] C t = f t ⊙ C t-1 + i t ⊙ tanh(W cx x t + W ch h t-1 + b c ), where ⊙ represents element-wise multiplication, C t-1 is the memory cell state at the previous moment, W cx 、W ch are the weight matrices, b c is the bias term.

[0084] The output gate sub-unit determines the data finally output to the next layer according to the updated memory cell value C t and the current input data x t . By calculating o t = σ(W ox x t + W oh h t-1 + b o ) to obtain the output gate value o t , W ox 、W oh are the weight matrices, b o is the bias term. The final output h t = o t ⊙ tanh(C t ), h t will be output as the aging output value of the current LSTM layer and passed to the aging output layer. In this way, the LSTM layer can effectively process the time-related data of the second input layer, capture the long-term dependencies therein, and provide strong support for determining the aging frequency compensation value later.

[0085] The method for outputting the aging frequency compensation value after performing weighted summation processing on the at least one aging output value in the aging output layer unit is as follows:

[0086] Assume that the last LSTM layer outputs n eigenvalue, which are respectively denoted as l 1 、l 2 、······l n ,

[0087] According to the formula y a = u 1 l 1 + u 2 l 2+ ······ + u n l n ,y a is the aging frequency compensation value, l 1 、l 2 、l n are the aging output values, u 1 、u 2 、u n are for l 1 、l 2 、l n corresponding weights.

[0088] S4. The fusion layer of the fusion neural network model fuses the temperature frequency compensation value and the aging frequency compensation value and then outputs the frequency adjustment value of the hemispherical resonator.

[0089] In the fusion neural network model, the temperature frequency compensation value output by the temperature compensation multi-layer perceptron unit and the aging frequency compensation value output by the aging compensation long short-term memory network unit are transmitted to the fusion layer. In the fusion layer, through the formula y = w T yt + w A y a weighted summation combines the two, and finally obtains the frequency adjustment value of the hemispherical resonator considering both temperature and aging factors, which is used to correct the original output frequency of the hemispherical resonator. According to the corrected frequency value, the measured temperature value is deduced, improving the temperature measurement accuracy and making the temperature measurement error smaller.

[0090] After the fusion layer of the fusion neural network model fuses the temperature frequency compensation value and the aging frequency compensation value and outputs the frequency adjustment value of the hemispherical resonator, it is judged whether the output frequency adjustment value of the hemispherical resonator is accurate;

[0091] The method for judging whether the output frequency adjustment value of the hemispherical resonator is accurate is as follows:

[0092] Obtain the true resonator frequency value of the hemispherical resonator without the influence of temperature and aging;

[0093] A high-precision frequency standard source can be used to measure the frequency of the hemispherical resonator as the true value in an ideal environment with strict control of temperature and aging factors being zero;

[0094] Obtain the frequency adjustment value of the hemispherical resonator output by the fusion neural network model; output the frequency adjustment value of the hemispherical resonator output by the fusion neural network model;

[0095] Judge whether the difference between the true resonator frequency value and the corrected resonator frequency is within the preset threshold; compare the difference between the true value of the frequency of the hemispherical resonator and the output frequency adjustment value of the hemispherical resonator with the preset threshold;

[0096] If so, it proves that the frequency adjustment value of the hemispherical resonator is accurate. If the difference is within the preset threshold range, it proves that the frequency adjustment value of the hemispherical resonator is accurate. If the difference is outside the preset threshold range, it proves that the frequency adjustment value of the hemispherical resonator is inaccurate. Moreover, the smaller the difference, the more accurate the frequency adjustment value of the hemispherical resonator.

[0097] The fusion neural network model obtains the compensated temperature value based on the frequency adjustment value of the hemispherical resonator.

[0098] It is known that the frequency of the hemispherical resonator and the temperature usually have a relationship such as F = F 0 (1 + α△T + β△T 2 ), where F is the actual frequency, F 0 is the initial frequency, α and β are coefficients related to the material, and △T is the temperature change.

[0099] After the fusion layer obtains the frequency adjustment value △F of the hemispherical resonator, the temperature change △T can be inversely deduced according to the above formula, that is, by solving the equation about △T. It is transformed into a quadratic equation of one variable, △F = F - F 0 = F 0 (α△T + β△T 2 ), and the root formula is used to solve △T. After obtaining △T, according to the requirements of temperature compensation, the temperature-related parameters in the system are adjusted. For example, if the temperature value is T, the compensated temperature value T 补 = T - △T.

[0100] In this way, through the temperature measurement error correction method based on the hemispherical resonator, the present application obtains the current measurement data of the hemispherical resonator in the current measurement environment and uploads it to the data storage center and the fusion neural network model. The temperature compensation multi-layer perceptron unit of the fusion neural network model outputs the temperature-frequency compensation value of the hemispherical resonator, and the aging compensation long short-term memory network unit of the fusion neural network model outputs the aging frequency compensation value of the hemispherical resonator. The fusion layer of the fusion neural network model fuses the temperature-frequency compensation value and the aging frequency compensation value and then outputs the frequency adjustment value of the hemispherical resonator. At the same time, temperature compensation and aging compensation are performed on the hemispherical resonator, thereby improving the accuracy of the hemispherical resonator compensation and effectively improving the measurement accuracy of the hemispherical resonator.

[0101] Please refer to Figure 2 , in the second aspect, the present application also provides a computer device 4, including a processor 40 and a memory 41. The memory 41 is used to store a computer program 42, and when the computer program 42 is executed by the processor 40, it implements the above-mentioned temperature measurement error correction method based on the hemispherical resonator.

[0102] The computer device 4 may be a computing device such as a tablet computer, a desktop computer, and a cloud server. The computer device may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art can understand that Figure 2 merely an example of the computer device 4, which does not constitute a limitation on the computer device 4, may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0103] The so-called processor 40 may be a central processing unit (CPU), and the processor 40 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0104] The memory 41 may be an internal storage unit of the computer device 4 in some embodiments, such as the hard disk or memory of the computer device 4. The memory 41 may also be an external storage device of the computer device 4 in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 4. Further, the memory 41 may also include both the internal storage unit and the external storage device of the computer device 4. The memory 41 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 41 may also be used to temporarily store data that has been output or will be output.

[0105] In a fourth aspect, the present application also provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the temperature measurement error correction method based on a hemispherical resonator is implemented.

[0106] The embodiments of the present application provide a computer program product, and when the computer program product runs on a computer device, the computer device is caused to execute the steps in the above-mentioned method embodiments.

[0107] In several embodiments provided by the present application, it can be understood that each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, the program segment, or the part of code includes one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the block may occur in a different order from that marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved.

[0108] If the described function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0109] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present application. It should be understood that the above description is only for the specific embodiments of the present application and is not used to limit the protection scope of the present application. In particular, it is pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A temperature measurement error correction method based on a hemispherical resonator, characterized in that: Acquire current measurement data of the hemispherical resonator in the current measurement environment and upload it to the data storage center and the fusion neural network model; the current measurement data includes at least one temperature value of the hemispherical resonator in the current measurement environment and the accumulated usage time of the hemispherical resonator; The data storage center is used to store the current measurement data and the historical measurement data of the hemispherical resonator; The fusion neural network model is an artificial intelligence model trained based on historical measurement data; Outputting the temperature frequency compensation value of the hemispherical resonator through the temperature compensation multilayer perceptron unit of the fusion neural network model; Outputting the aging frequency compensation value of the hemispherical resonator through the aging compensation long short-term memory network unit of the fusion neural network model; The fusion layer of the fusion neural network model fuses the temperature frequency compensation value and the aging frequency compensation value and outputs the frequency adjustment value of the hemispherical resonator; The fused neural network model obtains a compensated temperature value according to the frequency adjustment value of the hemispherical resonator.

2. The temperature measurement error correction method based on the hemispherical resonator according to claim 1, characterized in that: The method for obtaining the current measurement data of the hemispherical resonator in the current measurement environment and uploading it to the data storage center and the fusion neural network model includes: Obtain the temperature values ​​of different positions of the hemispherical resonator in the current measurement environment and upload them to the data storage center and the fusion neural network model; The accumulated usage time of the hemispherical resonator in the current measurement environment of the hemispherical resonator is obtained and uploaded to the data storage center and the fusion neural network model.

3. The temperature measurement error correction method based on the hemispherical resonator according to claim 1, characterized in that: The method of outputting the temperature frequency compensation value of the hemispherical resonator through the temperature compensation multilayer perceptron unit of the fusion neural network model includes: Input at least one temperature value as an input node in the first input layer; Each neuron in the hidden layer receives different temperature values ​​from the first input layer, and outputs the temperature data value after weighted average summation according to preset weights to the temperature compensation output layer; The temperature compensation output layer performs weighted average summation of the temperature data values ​​and outputs a temperature frequency compensation value.

4. The temperature measurement error correction method based on the hemispherical resonator as claimed in claim 3, characterized in that: The temperature data value formula obtained by weighted average summation according to the preset weights is: S1=W1T1+W2T2+W3T3+······+W N T N , T1, T2, T3, T N is the temperature value, W1, W2, W3, W N T1, T2, T3, T N The corresponding weights respectively.

5. The temperature measurement error correction method based on the hemispherical resonator as claimed in claim 4, characterized in that: The calculation formula for outputting the temperature frequency compensation value after weighted average summation of the temperature data values ​​is: yt=V1S1+V2S2+V3S3+······+V N S N , S1, S2, S3, S N is the temperature data value output by the hidden layer, V1, V2, V3, V N S1, S2, S3, S N The corresponding weights respectively.

6. The temperature measurement error correction method based on the hemispherical resonator as claimed in claim 5, characterized in that: The method of outputting the aging frequency compensation value of the hemispherical resonator through the aging compensation long short-term memory network unit of the fusion neural network model comprises: Input the accumulated usage time of the hemispherical resonator and / or the operation time of the hemispherical resonator after the last maintenance in the second input layer; The accumulated usage time of the hemispherical resonator and / or the operation time of the hemispherical resonator after the last maintenance are input into the LSTM layer unit as time node data; The time node data is processed by the input gate subunit, the forget gate subunit, the memory unit, and the output gate subunit in the LSTM layer unit, and outputs at least one aging output value, and outputs the aging output value to the aging output layer unit; At least one aging output value is subjected to weighted summation processing in the aging output layer unit to output an aging frequency compensation value.

7. The temperature measurement error correction method based on the hemispherical resonator according to claim 6, characterized in that: The method of outputting at least one aging output value after the time node data is processed by the LSTM layer unit through the input gate subunit, the forget gate subunit, the memory unit, and the output gate subunit, and outputting the aging output value to the aging output layer unit includes: Obtain the input gate value through the input gate subunit calculation; Obtain the forget gate value through the forget gate subunit calculation; The memory cell value is calculated by inputting the gate value and the forget gate value; The output gate subunit calculates the aging output value based on the time node data and the memory unit value.

8. The temperature measurement error correction method based on the hemispherical resonator according to claim 7, characterized in that: The method of outputting the aging frequency compensation value after the at least one aging output value is weighted summed in the aging output layer unit is: According to the formula y a =u1l1+u2l2+······+ u n l n ,y a is the aging frequency compensation value, l1, l2, l n is the aging output value, u1, u2, u n is l1, l2, l n The corresponding weight.

9. The temperature measurement error correction method based on the hemispherical resonator according to claim 8, characterized in that: In the fusion layer, the formula y = w T yt + w A y a Calculate the frequency adjustment value of the hemispherical resonator, w T and w A is the fusion layer weight.

10. The temperature measurement error correction method based on a hemispherical resonator according to claim 1, characterized in that: After the fusion layer of the fusion neural network model fuses the temperature frequency compensation value and the aging frequency compensation value and outputs the frequency adjustment value of the hemispherical resonator, it is determined whether the output frequency adjustment value of the hemispherical resonator is accurate.

11. The temperature measurement error correction method based on a hemispherical resonator according to claim 10, characterized in that: The method for judging whether the frequency adjustment value of the output hemispherical resonator is accurate is: Get the real resonator frequency value of the hemispherical resonator without the influence of temperature and aging; Obtain the frequency adjustment value of the hemispherical resonator output by the fusion neural network model; Determine whether the difference between the actual resonator frequency value and the corrected resonator frequency is within a preset threshold; If yes, it proves that the frequency adjustment value of the hemispherical resonator is accurate.

12. A computer device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the temperature measurement error correction method based on a hemispherical resonator is implemented as claimed in any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that: It stores a computer program, and when the computer program is executed by a processor, the temperature measurement error correction method based on a hemispherical resonator as claimed in any one of claims 1 to 11 is implemented.

Images